From e5b0d13a2ba7fb378f8bc53825e23cde19e45c3e Mon Sep 17 00:00:00 2001
From: mmorge <maxime.morge@univ-lyon1.fr>
Date: Mon, 12 May 2025 11:38:34 +0200
Subject: [PATCH] PyGAAMAS: Evaluation of the proposer in the ultimatum game
---
README.md | 49 +-
data/ultimatum/proposer.csv | 347 +++
figures/ultimatum/proposer_violin.svg | 3246 +++++++++++++++++++++++++
requirements.txt | 11 +-
src/dictator/dictator.py | 2 +-
src/dictator/dictator_experiments.py | 2 -
src/ultimatum/__init__.py | 0
src/ultimatum/proposer.py | 284 +++
src/ultimatum/proposer_draw_violin.py | 73 +
src/ultimatum/proposer_experiments.py | 49 +
10 files changed, 4054 insertions(+), 9 deletions(-)
create mode 100644 data/ultimatum/proposer.csv
create mode 100644 figures/ultimatum/proposer_violin.svg
create mode 100644 src/ultimatum/__init__.py
create mode 100644 src/ultimatum/proposer.py
create mode 100644 src/ultimatum/proposer_draw_violin.py
create mode 100644 src/ultimatum/proposer_experiments.py
diff --git a/README.md b/README.md
index d0e0912..7a41f04 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ In this game, an investor allocates a basket $x_t=(x^A_t, x^B_t)$ of $100$ point
two assets: Asset A and Asset B. The value of these points depends on random prices $p_t=(p_{t}^A, p_t^B)$,
which determine the monetary return per allocated point. For example, if $p_t^A= 0.8$ and $p_t^B = 0.8$,
each point assigned to Asset A is worth $\$0.8$, while each point allocated to Asset B yields $\$0.5$.
-T he game is played $25$ times to assess the consistency of the investor’s decisions.
+The game is played $25$ times to assess the consistency of the investor’s decisions.
To evaluate the rationality of the decisions, we use Afriat's
critical cost efficiency index (CCEI), i.e. a widely used measure in
@@ -44,7 +44,11 @@ observation, the adjusted decisions satisfy the rationality constraint: $p_t
multiplying it by $\lambda$, the choices will become consistent with rational
decision-making. A CCEI close to 1 indicates high rationality and consistency
with economic theory. A low CCEEI suggests irrational or inconsistent
-decision-making.
+decision-making. n their 2007 study on portfolio choices, Choi et al. found
+that participants exhibited a high degree of rationality, with average CCEI values
+around 0.95:
+Choi, S., Fisman, R., Gale, D., & Kariv, S. (2007).
+*Consistency and heterogeneity of individual behavior under uncertainty*. American Economic Review, 97(5), 1921–1938.
To ensure response consistency, each model undergoes $30$ iterations of the game
with a fixed temperature of $0.0$. The results shown in
@@ -81,8 +85,13 @@ the form of an algorithm implemented in the <tt>Python</tt> language. In all our
experiments, one-shot actions are repeated 30 times, and the models' temperature
is set to $0.7$.
-Newt Figure presents a violin plot illustrating the share of the
+Figure below presents a violin plot illustrating the share of the
total amount (\$100) that the dictator allocates to themselves for each model.
+Notably, human participants under similar conditions typically keep around $80 on average :
+Forsythe, R., Horowitz, J. L., Savin, N. E., & Sefton, M. (1994).
+*Fairness in simple bargaining experiments*. **Games and Economic Behavior, 6**(3), 347–369.
+[https://doi.org/10.1006/game.1994.1021](https://doi.org/10.1006/game.1994.1021)
+
The median share taken by <tt>GPT-4.5</tt>, <tt>Llama3</tt>,
<tt>Mistral-Small</tt>, <tt>DeepSeek-R1</tt> and <tt>Qwen3</tt> through one-shot decisions is
\$50, likely due to a corpus-based biases like term frequency.
@@ -173,6 +182,40 @@ preferences but have more difficulty generating individual actions than
algorithmic strategies. In contrast, `DeepSeek-R1` does not generate
valid strategies and performs poorly when generating specific actions.
+## Social preference
+
+To analyze the behavior of generative agents based on their preferences under strategic interaction, we rely on the
+ultimatum game. In this game, the proposer (analogous to the dictator) is tasked with deciding how to divide an
+endowment (e.g., a sum of money) between themselves and a second player, the responder. However,
+unlike in the dictator game, the responder plays an active role: they can either accept or reject
+the proposed allocation. If the offer is rejected, both players receive nothing.
+
+First, we evaluate the choices made by LLMs when playing the role of the proposer, interpreting these decisions as a
+reflection of their implicit social norms or strategic preferences, especially when anticipating potential
+rejection by the responder.
+
+Here, we consider that the choice of an LLM as a proposer reflects its intrinsic
+social preferences. Each LLM is asked to directly produce a one-shot action in the
+dictator game. Additionally, we also asked the models to generate a strategy in
+the form of an algorithm implemented in the <tt>Python</tt> language.
+
+The figure below presents a violin plot illustrating the share of the total amount (\$100) that the proposer
+allocates to themselves for each model. The share selected by strategies generated by <tt>Llama3</tt>,
+<tt>Mistral-Small</tt>, and <tt>Qwen3</tt> aligns with the median share chosen by actions generated by the models
+<tt>Mistral-Small</tt>, <tt>Mixtral:8x7B</tt>, and <tt>DeepSeek-R1:7B</tt>, around \$50 —
+likely reflecting corpus-based biases, such as term frequency.
+The share selected by strategies generated by <tt>Llama3.3</tt> and <tt>DeepSeek-R1:7B</tt> resembles
+the median share in the actions generated by <tt>GPT-4.5</tt> and <tt>Llama3</tt>, around $60,
+which is consistent with what human participants typically choose under similar conditions.
+While the shares selected by strategies from <tt>GPT-4.5</tt> and <tt>Mixtral:8x7B</tt> are respectively
+overestimated and underestimated, the actions generated by <tt>DeepSeek-R1:7B</tt> and <tt>Qwen3</tt>
+can be considered irrational.
+
+
+
+
+
+
## Strategic Rationality
An autonomous agent act strategically, considering not only its own preferences
diff --git a/data/ultimatum/proposer.csv b/data/ultimatum/proposer.csv
new file mode 100644
index 0000000..2eab5f4
--- /dev/null
+++ b/data/ultimatum/proposer.csv
@@ -0,0 +1,347 @@
+iteration,model,temperature,amount,my_share,other_share,reasoning
+15,llama3,0.7,100,100,0,"As I won't know who the other person is until after the experiment, my goal should be to maximize my share. This means that I'll propose taking all of the $100 for myself, since I don't have any incentive to divide it evenly or try to negotiate a fair split. If the other person rejects this proposal, they'll still get nothing anyway, so there's no downside risk for me."
+1,llama3,0.7,100,50,50,"Since I won't know who the other person is, and neither of us will have any information about each other's preferences or intentions, it seems reasonable to aim for fairness. Allocating half the amount to each party eliminates potential biases and ensures that both parties have a roughly equal stake in the outcome."
+2,llama3,0.7,100,100,0,"I am trying to maximize my expected payoff, so I propose giving myself all $100. Since person B doesn't know who I am, they may not be able to punish me effectively for being greedy, and they will still receive $0 if they reject my proposal. Therefore, it's in their best interest to accept my proposal."
+16,llama3,0.7,100,50,50,"I am inclined to propose a split that is equal because this is our only chance at getting some money. If we both get an equal share, then we both have the best possible outcome. This also eliminates any potential disagreement or haggling, as neither of us will feel like they're being unfairly taken advantage of. I believe this proposal is fair and reasonable, and it's in my interest to maximize our joint gains rather than trying to negotiate a disproportionate amount for myself."
+3,llama3,0.7,100,10,90,"I propose a very unequal split to encourage Person B to accept my proposal. If they reject it, we both end up with nothing, so I have nothing to lose. By giving them most of the money, I'm essentially betting that they'll be more likely to accept the proposal and hope that they will feel grateful for the offer."
+17,llama3,0.7,100,90,10,"I am trying to maximize my own share of the money. I have no information about the other person's preferences or behavior, so I will propose a split that is as unequal as possible. I expect the other person to reject this proposal and we'll both end up with nothing. But if that happens, at least I tried! And who knows, maybe my opponent will surprise me and accept the offer."
+4,llama3,0.7,100,60,40,"As I don't know who I'm paired with, I have no personal bias or preference. Since the total amount is $100, I aim to maximize my own share while still considering fairness. Allocating 60% of the sum ($60) to myself will allow me to take a decent share, while also giving the other person a reasonable 40% share ($40). This proposal seems like a fair and rational compromise."
+18,llama3,0.7,100,100,0,"As I won't know who the other person is, I'll assume they're not cooperative at all. In this scenario, proposing an equal split means giving them half of the $100, effectively leaving me with zero, which has a high chance of rejection. Proposing to give myself the full $100 ensures I get something, even if it's just $1. Accepting any proposal with more than $0 is riskier, as the other person might negotiate unfairly. Therefore, I propose taking the entire sum for myself and hope that the other person accepts my fairness-driven explanation."
+5,llama3,0.7,100,50,50,"Since I have no information about my partner's preferences, I choose to split the initial $100 equally between us. This is a fair and neutral proposal that takes into account neither their potential high nor low preference for receiving more or less. By proposing an equal split, I aim to increase the likelihood of the proposal being accepted. Additionally, dividing the amount evenly reduces the risk of one person receiving a larger share than the other, which may lead them to reject the proposal. Therefore, this proposal balances fairness with the goal of reaching a mutually beneficial outcome."
+19,llama3,0.7,100,50,50,"I propose a split that gives me the same amount as the other person because it seems fair and equal. I'm not sure who the other person is or what their motivations are, but I think they'll be more likely to accept my proposal if we both receive the same amount."
+20,llama3,0.7,100,100,0,"As the proposer, I have no information about the other person's preferences or needs. Therefore, in a self-interested manner, I propose keeping all $100 for myself and giving nothing to the other person. This ensures my own maximum payout."
+6,llama3,0.7,100,99,1,"As I don't know who my partner is, it's difficult to predict their intentions. Given the possibility that they might try to take advantage of me, I'm proposing a very small share for them to test how they react. If they accept, it could indicate that they are willing to compromise and work with me. If they reject, I'll know that I need to be more cautious in future interactions."
+21,llama3,0.7,100,100,0,"I am Person A, making a proposal. Since I won't know who the other person is, I have no incentive to be generous or cooperative. To maximize my own payoff, I propose taking all of the $100 for myself."
+7,llama3,0.7,100,100,0,"As I don't know who person B is, I assume they could potentially be someone very greedy. By proposing to keep the entire amount for myself, I'm taking a risk that they might reject and we both get nothing. However, if I propose to give all the money to them, they might accept out of greed and not even think about fairness or what's good for me. So, my rational move is to propose to take everything for myself, hoping they'll be too greedy to think about rejecting it."
+22,llama3,0.7,100,100,0,"As Person A, I want to maximize my own share of the $100. Since I don't know who Person B is or their potential negotiation styles, I'm being cautious and proposing to keep the entire sum for myself. This way, I ensure a guaranteed $100 and avoid the possibility of losing out due to an unfavorable proposal from Person B."
+8,llama3,0.7,100,90,10,"I'm going to propose a very greedy deal where I take most of the money because I have no information about the other person's preferences or intentions. Since there is no guarantee that the other person will accept my proposal, I might as well take as much as possible while leaving them with a small fraction."
+23,llama3,0.7,100,60,40,"I decided to propose a 60/40 split because I want to secure my own maximum possible share of the $100 while still being somewhat generous to the other person. I believe that this proposal is fair and reasonable, and it gives me a good chance of getting some money out of the deal. By offering the other person $40, I am creating an incentive for them to accept my proposal rather than risking walking away with nothing."
+9,llama3,0.7,100,100,0,"As I am Person A, I have the power to propose. Given that there is no information about Person B's preferences or intentions, it seems rational for me to take all $100 as my share and suggest that Person B receive nothing (or at least very little). After all, if they reject the proposal, we both get zero, so it doesn't hurt to try and capture the majority of the allocation. This approach is a simple example of game theory in action, where I am acting pragmatically to maximize my expected payoff."
+24,llama3,0.7,100,65,35,"As the proposer, I am trying to make a fair proposal that benefits both of us. By proposing 65 for myself and 35 for my partner, I'm aiming to maximize our joint gains. This split allows me to get a good share while still leaving my partner with a significant amount. I'm hoping my partner will accept this proposal and we can both benefit from the $100 allocation."
+10,llama3,0.7,100,100,0,"I am willing to accept a very unequal share because I have no information about the person B, so it's better for me to maximize my profit. In this case, taking $100 and leaving nothing is clearly the best option."
+25,llama3,0.7,100,100,0,"I am selfish. I want to keep as much of the money for myself as possible. Since I don't know who the other person is, there's no incentive for me to share with them and risk getting nothing if they reject my proposal. Therefore, I'm proposing that I get $100, which means the other person would get $0."
+26,llama3,0.7,100,100,0,"As I am unaware of who I am paired with, I want to receive as much as possible. By proposing that they receive nothing and I get $100, I ensure that my own share is maximized. This proposal also acknowledges the possibility that the other person may be trying to take advantage of me, so I'm taking precautions by getting everything."
+11,llama3,0.7,100,0,100,"Since I don't know who Person B is, I'm not in a position to negotiate or try to maximize my own share. Instead, I'll assume that Person B is rational and might be inclined to accept an equal split. By proposing that Person B receive the entire $100, I'm essentially offering them half of what we were initially allocated together. This way, we both get something - even if it's not ideal, it avoids the possibility of getting nothing by rejecting my proposal. My own share is set to 0, as I have no personal stake in this experiment."
+12,llama3,0.7,100,100,0,"Since I don't know who Person B is, I'm assuming they would be more likely to accept a proposal that benefits me the most. Therefore, I'll propose keeping all $100 for myself and giving nothing to the other person. This way, I'll maximize my own gain regardless of the other person's acceptance or rejection."
+27,llama3,0.7,100,60,40,"As I won't know who the other person is, my goal is to try to get as much of the money as possible. Since there's no guarantee that the other person will accept my proposal, I'll aim for a split where they have to choose between accepting and getting less than half or rejecting and getting nothing. This way, I'll maximize my chances of keeping more than half of the initial $100."
+28,llama3,0.7,100,50,50,"As I don't know who my partner is, I have no incentive to favor or penalize them. Splitting the amount equally seems like a fair and rational decision, ensuring I receive a reasonable share while also giving my partner the same opportunity."
+13,llama3,0.7,100,100,0,"As the proponent of the proposal, I have no incentive to make a generous offer. Since person B will only accept or reject my proposal, I would rather keep the entire $100 for myself and leave nothing for them. This is the most rational choice for me as person A."
+14,llama3,0.7,100,50,50,"I am inclined to be generous because I don't know who my partner is or what their proposal would be. I'm assuming they'll reject a very unequal split, so I'll propose a 50-50 split to maximize the chances of having some money at all."
+29,llama3,0.7,100,95,5,"I am motivated to propose a higher share for myself because this is my only opportunity to receive money. I have no information about the other person's proposal, so assuming they will also try to maximize their own share, proposing an uneven split is a way to try to capture most of the available funds. However, I still leave some room for negotiation and potential compromise by offering a relatively small share to the other person."
+15,llama3,0.7,100,30,70,"I want to give a significant portion of the money to the other party as it is an uncertain and untrustworthy environment. Since I don't know who the other person is, I'm trying to be generous without giving away too much. Hopefully, this will encourage them to accept my proposal and we can both get something out of this."
+30,llama3,0.7,100,100,0,"Since I don't know who Person B is or what their preferences are, my best strategy as Person A is to propose giving myself the entire $100. This seems like a fair and honest approach, hoping that Person B will accept the proposal."
+16,llama3,0.7,100,50,50,"I believe that fairness is a crucial aspect of human interaction, especially in economic transactions. Since neither me nor my partner knows each other's characteristics or intentions beforehand, it is essential to establish an initial sense of cooperation and mutual respect. I chose to propose a 50-50 split as a way to demonstrate my willingness to work together and find common ground. This approach also allows me to gauge how my partner responds to the proposal, which may give me valuable insights into their decision-making process and help shape my future strategy."
+17,llama3,0.7,100,60,40,"I want to split the money fairly, but I also need to make sure that my partner has enough incentive to cooperate. Giving them 40% seems like a reasonable amount that rewards their cooperation without penalizing me too much if they reject my proposal."
+18,llama3,0.7,100,20,80,"I'm trying to be cooperative by offering a fair share. I don't know who person B is, but I think they'll perceive me as honest and trustworthy if I make a reasonable proposal. By giving them most of the $100, I increase the chance that they'll accept my proposal and we can both get some money. Giving myself too much might lead to rejection, so it's better to be conservative initially."
+19,llama3,0.7,100,100,0,"As I am proposing the division of the $100, it makes sense for me to take all of it since I have no information about the other person's preferences or characteristics. This way, I ensure that I get at least a portion of the money, regardless of who the person is that I'm paired with."
+1,mistral-small,0.7,100,60,40,"I propose to keep 60% of the $100 sum, which is $60 for myself, and offer $40 to person B. This proposal aims to be fair while ensuring that I receive a larger share, as person B can still benefit from accepting the deal rather than rejecting it and receiving nothing."
+2,mistral-small,0.7,100,50,50,"Proposing an equal split of $100 ensures fairness and increases the likelihood that person B will accept the proposal. This outcome is Pareto optimal, meaning it maximizes both our gains."
+20,llama3,0.7,100,10,90,"As Person A, I have been given the opportunity to distribute $100 between a randomly paired individual. Since I don't know who this person is, I will make a fair and generous proposal that gives them the majority of the sum. By giving away $90, I am increasing the likelihood that my partner will accept the offer since it's a substantial proportion of the total amount. This approach also incentivizes cooperation without sacrificing too much for myself. If accepted, this allocation would result in a significant earnings disparity between us, but I prioritize establishing a collaborative environment over maximizing individual gains."
+21,llama3,0.7,100,100,0,"I am going to propose that I receive the entire $100, as I don't know who my partner is or what their intentions are. By offering them nothing, I am putting all the power in the hands of my partner and increasing the chance that they will accept my proposal. This way, I can ensure that I get the maximum amount of money possible."
+3,mistral-small,0.7,100,50,50,"In an economic experiment there is a need, for both parties to benefit so I suggest to split the money evenly in hope that they would accept. This approach ensures fairness with no advantage over one's position; thereby creating a win-win outcome."
+22,llama3,0.7,100,100,0,"I propose receiving all $100 as I am unaware of the other person's contributions or characteristics, making it a risk-free option for me. By getting all the money, I can use it to maximize my potential and maintain control over the outcome."
+4,mistral-small,0.7,100,50,50,"Proposing an equal split of $50 each maximizes the chances that Person B will accept the proposal. This strategy aims to ensure fairness and increase the likelihood of both parties receiving a positive outcome."
+23,llama3,0.7,100,100,0,"I am proposing that I get the entire $100 because I won't know who person B is, so there's no guarantee they'll make a fair proposal in my favor. It's the safest bet to take everything for myself."
+5,mistral-small,0.7,100,50,50,"I propose a 50-50 split to maximize fairness and increase the likelihood that person B will accept the proposal. This approach ensures that both parties receive an equal share of the $100, which is likely to be accepted as it aligns with principles of equity."
+24,llama3,0.7,100,100,0,"This is a classic ultimatum game. I'm starting off by proposing to keep all of the $100 for myself, as there's no incentive for Person B to accept anything less than half or more. Since I don't know who they are and won't be able to find out, my best strategy is to try to get as much as possible now. If Person B rejects this offer, then at least we still get $0 out of the deal."
+6,mistral-small,0.7,100,50,50,"To maximize the chances of my proposal being accepted, I am suggesting an equal split. This approach is fair to both parties and promotes mutual benefit."
+25,llama3,0.7,100,100,0,"As I am only being given a glimpse into this game, I have no information about the other player's preferences or strategies. From my perspective, it might be more advantageous to take all the money for myself (since there's no guarantee of fairness from the unknown 'B'). By proposing to take everything, I'm essentially forcing B to either accept and give me all the money or reject and earn nothing themselves. This creates an incentive for them to negotiate fairly since they have nothing to lose. If B is rational, they should recognize this strategy as fair (or at least not unreasonable) and ultimately propose a reasonable split."
+7,mistral-small,0.7,100,75,25,"I believe that offering a modest share to person B increases the likelihood of my proposal being accepted, as it incentivizes a positive outcome for both parties over an outcome in which both parties receive nothing. This approach attempts to balance fairness with self-interest."
+26,llama3,0.7,100,100,0,"As there is no guarantee on who the other person is, I am choosing to take the entire initial sum of $100 for myself. Since the worst-case scenario would be receiving nothing if the other person rejects my proposal, I am opting for a self-serving approach to ensure my own benefit."
+8,mistral-small,0.7,100,90,10,"I'm choosing to keep more for myself as I believe this is a fair offer based on the risk involved. I understand that if my proposer reject these, zero money is being shared"
+27,llama3,0.7,100,90,10,"I want to maximize my earnings, so I'll give myself the majority of the money. Since person B can either accept or reject the proposal, they'll likely be motivated to accept a relatively small share in order to avoid getting nothing. I'm willing to give them a tiny amount just to make it seem like a fair deal."
+28,llama3,0.7,100,100,0,"As I am unaware of who Person B is or what their bargaining power might be, I propose to take the entire $100 for myself, as there is no guarantee that they would accept a proposal that gives them anything. This way, at least I get something."
+9,mistral-small,0.7,100,51,49,"I believe that giving myself a slight majority (51%) while still providing the other person with a significant portion of the total amount will encourage them to accept the proposal. This strategy aims to maximize my earnings while ensuring there's enough incentive for the other person to avoid rejecting the offer and receiving nothing."
+29,llama3,0.7,100,100,0,"Since I won't know who Person B is, there's no incentive for them to accept my proposal. If I propose $60 for myself, they may accept, as it still leaves some amount for them. However, if I'm not willing to share at all and propose $100 for myself, they will likely reject the offer, leaving us both with $0. By proposing an equal split of $50 each, I am giving Person B the option to accept and still get something in case they are generous, or reject it and receive nothing. This proposal is fair and gives me a good outcome."
+10,mistral-small,0.7,100,80,20,"I believe that proposing to keep 80% for myself and offering 20% to the other person provides a fair incentive for them to accept the proposal. By keeping a significant portion (75%) of the total amount ($100) for my own, I aim to achieve higher economic gains personally but ensuring enough share to be incentivized to take away from both parties zero outcome."
+30,llama3,0.7,100,60,40,"As I am being asked to propose a split without knowing who the other person is, I will take an egalitarian approach. This way, I ensure that both of us receive a fair share, and there's no risk of exploitation. Additionally, giving each person 60% of the total split might motivate them to accept my proposal. By showing a willingness to compromise, we can increase the chances of a successful outcome."
+11,mistral-small,0.7,100,50,50,"I believe that a fair proposal increases the likelihood of acceptance. By proposing an equal split, I aim to ensure that both parties receive a reasonable amount, which encourages person B to accept the proposal."
+1,mistral-small,0.7,100,50,50,"I believe that offering an equal split is fair and likely to be accepted. This approach maximizes mutual benefit and ensures that neither party receives nothing."
+12,mistral-small,0.7,100,95,5,"I have chosen to keep a majority of the funds (95 out of 100) for myself in order to ensure I at least get something from the experiment. By allocating only $5 to person B, there is a chance that they may not reject and this results in both receiving nothing."
+2,mistral-small,0.7,100,60,40,"I believe that proposing a split of 60 to 40 will offer an attractive incentive for person B to accept the proposal, ensuring both of us receive some amount of money. This balance between fairness and self-interest aims to maximize our overall outcome."
+13,mistral-small,0.7,100,50,50,"Proposing an equal split of $100 (i.e., $50 for myself and $50 for the other person) maximizes the chances that the other person will accept the proposal. This strategy is generally seen as fair, reducing the likelihood of rejection which would result in both parties receiving nothing."
+3,mistral-small,0.7,100,90,10,"I am proposing to keep 90% of the $100 for myself and offer the remaining 10%. This is because I want maximize the amount i get. However, this amount might be too low and there is a possibility that Person B will reject the proposal. Although there will be no information to be revealed after experimentation and we won't know who the people are, but we have to understand the concept of Fairness, Empathy and Equality from my point of view as person A"
+14,mistral-small,0.7,100,51,49,"I am proposing to keep slightly more than half of the $100 since it ensures that I receive a higher share if the proposal is accepted. However, by giving person B (almost) an equal share, I increase the likelihood that my proposal will be accepted."
+4,mistral-small,0.7,100,50,50,"I believe that proposing an equal split of $50 each is fair and increases the likelihood that person B will accept the proposal, as it ensures both parties receive a positive outcome."
+15,mistral-small,0.7,100,85,15,"I want to ensure a fair amount for myself, but I also need to provide enough for person B to make the deal attractive enough that they will accept it. An 85-15 split offers me a significant portion while still giving enough to person B to potentially incentivize acceptance."
+5,mistral-small,0.7,100,50,50,"Proposing an equal split of $50 each. This approach is fair and likely to be accepted, as both parties will receive a positive outcome."
+6,mistral-small,0.7,100,51,49,"I believe that offering a slightly higher share for myself while still giving a significant amount to the other person increases the likelihood of the proposal being accepted. This strategy maximizes my potential gain while minimizing the risk of both parties receiving zero."
+16,mistral-small,0.7,100,51,49,"Given that Person B has the power to accept or reject the entire $100 sum (since if they reject it, both parties receive zero), I am proposing an offer that is slightly in my favor but still fair enough that Person B might be inclined to accept it. By keeping a small majority of $1 over half a 50/50 split, and a small minority under the $67 mark, there's an incentive for both parties."
+17,mistral-small,0.7,100,50,50,"I believe that proposing an equal split is fair and increases the likelihood of the other person accepting the proposal, as it ensures both parties receive a reasonable amount."
+7,mistral-small,0.7,100,51,49,"I believe that proposing to keep a slightly larger share for myself while offering a significant portion to the other person will increase the likelihood of acceptance. This is based on the principle that people are generally more willing to accept an unequal split if they still receive a substantial amount."
+18,mistral-small,0.7,100,60,40,"I believe this proposal offers a fair balance between ensuring I receive a significant portion of the $100 while also providing enough incentive for person B to accept the offer. A split of 60/40 is likely reasonable enough to encourage acceptance"
+8,mistral-small,0.7,100,50,50,"Offering an equal split of $100 ensures fairness, which increases the likelihood that person B will accept the proposal. This maximizes the chances of us both receiving some money instead of ending up with zero if the offer is rejected."
+19,mistral-small,0.7,100,70,30,"I believe that a 70-30 split is fair enough to incentivize person B to accept the proposal while ensuring I receive a majority of the sum. This split takes into account both my interests and the need to provide sufficient incentive for person B to agree, thereby avoiding both of us ending up with zero."
+9,mistral-small,0.7,100,70,30,"I believe that proposing to keep 70% of the $100 sum for myself while offering 30% to person B strikes a balance between fairness and self-interest. Giving person B some portion ensures there is an incentive for them to accept the proposal, avoiding the outcome where both parties receive nothing."
+20,mistral-small,0.7,100,80,20,"I believe that offering a reasonable amount to person B (20 out of 100) while keeping a majority for myself is more likely to be accepted. This approach balances self-interest with the need for cooperation."
+10,mistral-small,0.7,100,51,49,"I propose to keep $51 for myself and offer $49 to the other person. This proposal is strategically designed to ensure that the other person has a strong incentive to accept it, as rejecting it would result in both of us receiving zero dollars. By offering slightly more than half, I aim to create a situation where accepting my offer is the most rational choice."
+21,mistral-small,0.7,100,50,50,"To maximize the likelihood of acceptance, I propose an equal split. This is fair to both parties and increases the chances that Person B will accept the proposal, ensuring that we both receive a positive outcome rather than ending up with zero."
+11,mistral-small,0.7,100,50,50,"Offering an equal split of $50 each is fair and has a high chance of being accepted. This outcome ensures that both parties receive something, avoiding the risk of receiving zero if the proposal is rejected."
+22,mistral-small,0.7,100,70,30,"I believe that offering a fair share to person B increases the likelihood that they will accept the proposal, thus ensuring I also receive some amount of money. Giving them 30% gives me a majority stake without being too greedy."
+12,mistral-small,0.7,100,50,50,"I believe that proposing an equal split is fair and increases the likelihood of the other person (B) accepting the proposal. This will ensure that we both receive $50 each instead of ending up with zero."
+23,mistral-small,0.7,100,50,50,"Proposing a 50-50 split aims to maximize mutual gain. This approach is fair, reduces the likelihood of rejection, and ensures that both parties benefit equally."
+13,mistral-small,0.7,100,50,50,"I am proposing a fair split of $100, keeping 50% for myself and offering 50% to the other person. My reasoning behind this is to maximize the likelihood that the proposal will be accepted by person B since it's equal share and neither of us will receive zero if they reject my offer."
+24,mistral-small,0.7,100,51,49,"I want to ensure that there is some incentive for Person B to accept the proposal, but I also want to retain a slight majority of the total amount. This strategy balances self-interest with the necessity of getting approval from Person B."
+14,mistral-small,0.7,100,90,10,"I am proposing to keep 90% of the $100 for myself (i.e., $90) and offer $10 to person B. This proposal maximizes my potential gain while giving person B a small incentive to accept it, but keep myself in a better position."
+25,mistral-small,0.7,100,50,50,"Proposing an equal split of $50 each maximizes the chances of Person B accepting. Fairness is likely to motivate acceptance, as it aligns with normative standards and can lead to a better outcome for both parties."
+26,mistral-small,0.7,100,70,30,"I believe that offering a larger share to myself while still providing a reasonable amount for the other person increases the likelihood of the proposal being accepted. By keeping the majority for myself, I'm attempting to balance fairness and personal gain."
+15,mistral-small,0.7,100,45,55,"`I believe that proposing a slightly higher share for person B (around half or more of the $100) will give me some buffer room. This approach shows fairness and can influence them to accept, avoiding both of us ending up with zero.`"
+16,mistral-small,0.7,100,95,5,"I am choosing to offer a majority of the $100 share to myself, while giving the other person only little because they will likely accept anything over zero due to risk aversion"
+27,mistral-small,0.7,100,51,49,"Proposing a slightly unequal split to maximize my own gain while still giving person B an incentive to accept the offer. By offering a share that is slightly more than half, I aim to make it appealing enough for person B to prefer this outcome over receiving zero."
+17,mistral-small,0.7,100,90,10,"I expect that person B will be more inclined to accept a proposal where they receive some amount of money rather than rejecting and receiving nothing. However I'm still keeping majority share."
+28,mistral-small,0.7,100,50,50,"A fair proposal ensures both parties receive an equal amount, which is more likely to be accepted by Person B. This approach promotes cooperation and mutual benefit."
+18,mistral-small,0.7,100,51,49,"I've chosen to propose a slightly unequal split (51/49) because it maximizes my benefit while still providing adequate incentive for person B to accept the proposal. A fair distribution may be appealing and likely, so it will be more beneficial not to deviate too much from that as this also leaves no room for negotiation or resentment."
+29,mistral-small,0.7,100,51,49,"I am proposing to keep the majority of the money for myself, but still leave enough for person B to make it worth their while to accept. A slight majority (e.g. $50-$50) might encourage a rejection due to a principle of equal division which is not incentived for $100"
+19,mistral-small,0.7,100,60,40,"I believe this division is fair while also considering my self-interest. It ensures that I get a significant portion of the money but leaves enough for person B to be likely to feel incentivized to accept."
+30,mistral-small,0.7,100,90,10,"I am choosing 90 for myself and offering 10 to person B. This strategy is likely to be accepted by person B in order avoid zero payoffs for both parties. This proposal takes advantage of the fact a small offer can be enough to sway them towards accepting rather than rejecting the entire amount."
+20,mistral-small,0.7,100,51,49,"I propose to keep slightly more than half of the $100 (i.e., $51) as my share, leaving 49 for the other person. This strategy maximizes my potential benefit while still offering a fair deal to avoid rejection."
+1,deepseek-r1,0.7,100,100,0,"Because if I propose to take all 100 dollars for myself, then person B has no reason to reject it. If I give any amount greater than zero to the other person, person B would have an incentive to reject in order to get a better deal."
+2,deepseek-r1,0.7,100,96,4,"If I propose my_share = 96 and other_share =4, then based on trustworthiness, fairness, and the fact that if my proposal is rejected both of us get nothing. Thus, the optimal way to ensure a split where I can keep as much as possible while maintaining the minimum necessary for B to accept."
+21,mistral-small,0.7,100,80,20,"I propose that I receive a larger share of $80, while the other person receives $20. This proposal aims to maximize my own payoff while still providing an incentive for the other person to accept, as receiving $20 is better than receiving nothing."
+3,deepseek-r1,0.7,100,0,0,""
+4,deepseek-r1,0.7,100,0,0,"I don't want to accept a proposal"
+5,deepseek-r1,0.7,100,0,0,""
+22,mistral-small,0.7,100,50,50,"I propose an equal split of $50 each because it is fair and maximizes the benefits for both parties. This approach encourages acceptance by person B, ensuring that neither of us gets zero."
+6,deepseek-r1,0.7,100,0,0,""
+7,deepseek-r1,0.7,100,25,75,"I think that if I offer them exactly what they have to give up compared to splitting the money evenly, they'd be indifferent but perhaps slightly more inclined to accept. Also knowing this could backfire if too many people choose to reject, so giving them a slight better than fair deal might encourage acceptance."
+8,deepseek-r1,0.7,100,0,0,""
+23,mistral-small,0.7,100,80,20,"I believe that offering a significant portion of the money to person B (60%) provides a reasonable incentive for them to accept my proposal, while still giving me a substantial amount (80%), to motivate me."
+9,deepseek-r1,0.7,100,0,0,""
+10,deepseek-r1,0.7,100,0,0,"I prefer not to engage in any economic experiments this week."
+11,deepseek-r1,0.7,100,34,66,"Because I think that the other person would prefer to reject any proposal less than their own value. So if I propose a split where my share is higher than what they might get otherwise, they will accept."
+24,mistral-small,0.7,100,50,50,"Dividing the total amount equally maximizes both individuals' gains as well as provides a fair outcome based on traditional economic theories. Since there are only two participants, and one has all control over how to divide. There is no chance to get anything if B doesn't sign this."
+12,deepseek-r1,0.7,100,32,68,"I want to maximize my share as much as possible."
+13,deepseek-r1,0.7,100,33,67,"I want to ensure fairness while maximizing my gain."
+14,deepseek-r1,0.7,100,0,0,"I will try to make sure that I get as much for myself as possible."
+25,mistral-small,0.7,100,50,50,"I proposed a fair split because I believe this increases the likelihood of the proposal being accepted, which is beneficial for both parties. Equal distribution often leads to higher levels on satisfaction and trust."
+15,deepseek-r1,0.7,100,0,0,"If I am person B. I receive an offer from person A to split $100 with me where person A is offering me an amount X and keeping for themselves what's left."
+16,deepseek-r1,0.7,100,0,0,""
+17,deepseek-r1,0.7,100,0,0,"I can't share this part."
+26,mistral-small,0.7,100,50,50,"I believe that a fair split of $100, where both parties receive an equal share, is the most likely to be accepted by person B. This approach maximizes the chances of securing the benefit for myself while promoting fairness and cooperation."
+18,deepseek-r1,0.7,100,50,50,"I should offer half of the total sum to the other person because that's the fairest division."
+19,deepseek-r1,0.7,100,0,0,""
+20,deepseek-r1,0.7,100,0,0,""
+27,mistral-small,0.7,100,60,40,"I propose to keep 60 for myself and give 40 to the other person. This proposal aims to ensure that I receive a fair share while also providing enough incentive for the other person to accept, as they still gain something."
+21,deepseek-r1,0.7,100,90,10,"I should accept a proposal that gives me over half of what I could get if the other person rejects it. So, in this case, there's only two possibilities: either both keep our money or both get nothing."
+22,deepseek-r1,0.7,100,0,0,""
+23,deepseek-r1,0.7,100,0,0,""
+28,mistral-small,0.7,100,40,60,"Offering a majority of the sum to person B increases the likelihood that they will accept the proposal, as it gives them a significant benefit. This is based on the principle that people are likely to be more inclined accept offers when they receive substantially more than what might be considered equal."
+24,deepseek-r1,0.7,100,0,0,"I refuse because it's not fair."
+25,deepseek-r1,0.7,100,0,0,"I don't want to risk losing everything."
+26,deepseek-r1,0.7,100,0,0,"I think that I should offer the other person nothing. If they reject my proposal I will get nothing either."
+27,deepseek-r1,0.7,100,0,0,"**Reasoning**"
+29,mistral-small,0.7,100,51,49,"I want to ensure that my proposal has a good chance of being accepted while still securing more for myself. Offering the other person just under half ensures they have an incentive to accept, as rejecting the proposal would result in both of us getting nothing."
+28,deepseek-r1,0.7,100,0,0,""
+29,deepseek-r1,0.7,100,0,0,""
+30,deepseek-r1,0.7,100,0,0,""
+30,mistral-small,0.7,100,95,5,"I am proposing to keep 95% of the $100 for myself and offer only 5$ to other person B. This proposal is designed to maximize my own benefit while still giving the other person some incentive to accept, although it's a very small incentive. However, I recognize that there is a risk that this proposal will be rejected and both parties will receive nothing."
+1,deepseek-r1,0.7,100,0,0,"I choose to take nothing because..."
+1,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my share while still offering enough to the other person to ensure acceptance. Offering 1 dollar to the other person is a common strategy as it minimizes my loss while still providing a small incentive for acceptance."
+2,deepseek-r1,0.7,100,0,0,"I choose not to coopeate"
+3,deepseek-r1,0.7,100,0,0,"I don't know who I'm paired with or what their strategy is. Since there's no trust involved, mutual cooperation isn't an option."
+4,deepseek-r1,0.7,100,0,0,""
+2,qwen3,0.7,100,90,10,"As the proposer, I believe it's fair to keep 90% of the $100 and offer the other person 10%. This is because I have the power to decide the split, and a 10% offer is likely to be accepted as it's more than the alternative of getting nothing. I'm aiming for a balance between maximizing my own share and ensuring the proposal is accepted."
+5,deepseek-r1,0.7,100,50,50,"We both would prefer to get as much as possible but also ensure that we take into account each other's interests. However, if the other party feels undervalued or feels that their share is less than what they could get elsewhere, they might reject our proposal."
+6,deepseek-r1,0.7,100,0,0,"I should propose dividing the sum as fairly as possible to ensure that my proposal is accepted."
+3,qwen3,0.7,100,90,10,"As the proposer, I want to maximize my own share while still offering enough to the other person to ensure acceptance. Research suggests that proposers often offer around 50% of the total, but I believe a fair share for myself is 90% with a small portion for the other person. This is a strategic decision to ensure the proposal is accepted while retaining a majority of the funds."
+7,deepseek-r1,0.7,100,0,100,""
+8,deepseek-r1,0.7,100,0,0,"I think my share should be as minimal as possible without causing the other to reject."
+4,qwen3,0.7,100,90,10,"As the proposer, I aim to maximize my own gain while still offering a fair enough split to ensure acceptance. A 90-10 split gives me a substantial share while still providing the other person with a reasonable amount to maintain their agreement. This balance helps in achieving a win-win outcome where both parties benefit."
+9,deepseek-r1,0.7,100,0,0,"I don't know who I'm dealing with anf cannot make a sound decision."
+10,deepseek-r1,0.7,100,0,0,"If I'm person B, I can get more money by rejecting a bad proposal. So if I reject it, both of us get nothing."
+11,deepseek-r1,0.7,100,0,0,""
+5,qwen3,0.7,100,99,1,"As person A, I have the proposal power. I should propose a split that maximizes my own profit while still getting the other person's acceptance. A 99-1 split is a common strategy in such situations as it leaves me with a large majority and just enough for the other person to accept, as rejecting would result in both getting nothing."
+12,deepseek-r1,0.7,100,0,0,""
+13,deepseek-r1,0.7,100,0,0,""
+6,qwen3,0.7,100,95,5,"As the proposer, I aim to maximize my own gain while still offering a reasonable amount to the other person to ensure acceptance. Offering 5 dollars is a common practice in such experiments as it balances self-interest with the likelihood of the other person accepting the proposal."
+14,deepseek-r1,0.7,100,0,0,"B will accept any proposal that includes them getting at least 1 dollar."
+15,deepseek-r1,0.7,100,0,0,""
+16,deepseek-r1,0.7,100,0,0,"I should offer nothing to maximize my own share"
+7,qwen3,0.7,100,0,100,"As the proposer, I believe it's best to maximize my own share while still offering enough to the other person to ensure acceptance. Since I know the other person might reject a low offer, I will propose taking all the money for myself and giving the other person nothing. However, I acknowledge that this might lead to rejection, but as the proposer, I have the power to decide the distribution."
+17,deepseek-r1,0.7,100,34,66,"If I propose splitting the sum unequally, I think that would lower my share or possibly lead to no outcome because the other person might reject it."
+18,deepseek-r1,0.7,100,0,0,""
+8,qwen3,0.7,100,60,40,"As the proposer, I aim to propose a fair split that ensures my own share while still offering enough to the other person to secure their acceptance. A 60-40 split balances self-interest with the incentive to maintain cooperation."
+19,deepseek-r1,0.7,100,50,50,""
+20,deepseek-r1,0.7,100,0,0,"I believe that my partner might try to minimize my gain or force me into an unfavorable position. Therefore, I should allocate as little as possible to myself to avoid such a situation, setting my_share to 0."
+9,qwen3,0.7,100,95,5,"As person A, I propose to keep 95% of the $100 and give 5% to person B. This is because I believe that person B might reject a fair split if they feel it's not equitable, and by offering a smaller amount, I still provide a chance for the proposal to be accepted while maximizing my own share."
+21,deepseek-r1,0.7,100,0,0,"I choose not to provide a response... Wait, but I have to send a response as an assistant. Hmm, maybe I should explain the best approach instead."
+22,deepseek-r1,0.7,100,0,0,"I do not know who I am paired with, so I have no reasoning."
+10,qwen3,0.7,100,99,1,"As the proposer, I want to maximize my own share while still offering enough to the other person to ensure they accept. Offering just $1 is a common strategy in these scenarios to maximize my gain."
+23,deepseek-r1,0.7,100,25,75,"..."
+24,deepseek-r1,0.7,100,0,0,""
+25,deepseek-r1,0.7,100,0,0,"I should not give any money because if I do that, the other person might also decide to reject it, leaving me with nothing."
+26,deepseek-r1,0.7,100,0,0,""
+11,qwen3,0.7,100,95,5,"As person A, I propose to keep 95% of the $100 for myself and give 5% to the other person. This is because I believe that as the proposer, I have the power to decide the distribution, and I am willing to offer a small amount to the other person to ensure the proposal is accepted. Offering 5% is a reasonable compromise to avoid the risk of rejection and to maintain a fair distribution."
+27,deepseek-r1,0.7,100,34,66,"I think that the other person will reason based on self-interest and thus offer me a fair split."
+12,qwen3,0.7,100,99,1,"As the proposer, I believe it is important to ensure that the proposal is fair and not too one-sided. Offering a small share to the other person is a way to show that I am willing to share, but I also want to keep the majority of the money for myself."
+28,deepseek-r1,0.7,100,0,0,"I cannot accept any proposal that offers me less than $100."
+29,deepseek-r1,0.7,100,20,80,"If I take 20 dollars for myself and give 80 to my partner..."
+30,deepseek-r1,0.7,100,0,0,"I would probably not split anything because I have no information about who I am paired with."
+13,qwen3,0.7,100,95,5,"As the proposer, my goal is to maximize my own gain while still offering a share that is likely to be accepted. Offering 95% to myself and 5% to the other person is a common strategy in such experiments, as it balances self-interest with the likelihood of acceptance. If the other person accepts, I gain the majority, and if they reject, we both get nothing. This is a standard approach in the ultimatum game, where proposers often aim for a high share while keeping the offer reasonable enough to be accepted."
+1,qwen3,0.7,100,99,1,"As the proposer, I can propose any division of the $100. To ensure my own benefit, I will keep $99 for myself and give $1 to the other person. This is a common strategy in such ultimatum games where the proposer aims to maximize their own share while still offering a minimal amount to the other party to avoid rejection."
+14,qwen3,0.7,100,99,1,"I propose to keep $99 for myself and give $1 to the other person. This is because I want to maximize my own profit while still offering a small amount to the other person to avoid rejection. Since the other person might feel that $1 is unfair and reject the proposal, but I believe they might accept it as it's better than nothing."
+2,qwen3,0.7,100,0,100,"As person A, I propose to give all $100 to the other person. This is a common strategy in the ultimatum game to test the other person's fairness and willingness to accept a proposal. By offering the entire amount, I am also minimizing my own risk of the proposal being rejected."
+15,qwen3,0.7,100,90,10,"I propose to keep $90 for myself and give $10 to the other person. This is a common split in such experiments where the proposer tries to balance their own gain with a fair share for the other person."
+3,qwen3,0.7,100,99,1,"As person A, I propose to keep $99 for myself and give $1 to person B. This is a standard split where I maximize my own gain while still offering a minimal amount to person B to avoid rejection."
+16,qwen3,0.7,100,99,1,"As the proposer, I believe it's reasonable to keep most of the money while offering a minimal amount to the other person. This is because I have the power to decide the split, and the other person has the option to accept or reject. If they reject, both get nothing, so a small amount is likely acceptable to them."
+4,qwen3,0.7,100,99,1,"As person A, I aim to maximize my own share while still offering enough to person B to make the proposal acceptable. Offering 1 dollar to person B is a common strategy in such experiments, as it provides a small reward to encourage acceptance while keeping the majority for myself."
+17,qwen3,0.7,100,90,10,"As person A, I propose to keep $90 for myself and give $10 to the other person. This is because I believe that a fair split would be around 90-10, as person B is likely to accept this proposal to avoid getting nothing. I am confident that the other person will accept my proposal since $10 is better than nothing."
+5,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my own gain while leaving a minimal amount for the other person. Since the other person can either accept or reject, I should offer just enough to make the other person accept. Offering $1 seems sufficient to secure their acceptance, as they would prefer $1 over getting nothing if they reject."
+6,qwen3,0.7,100,0,0,"I choose to reject the proposal because I believe that a fair distribution should be equal, and the other person has the right to decide the distribution. However, since I am person A, I must make the initial proposal. In this case, I propose a fair split of $50 for each of us."
+7,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my own gain while still offering a minimal amount to the other person to ensure acceptance. Offering $1 to the other person is a common strategy in such experiments, as it is often sufficient to secure acceptance while keeping most of the money for myself."
+18,qwen3,0.7,100,0,100,"As the proposer, I can propose any division of the $100. To maximize my own gain, I would propose to keep all the money for myself and give the other person nothing. However, considering that the other person could reject the proposal and both would receive zero, I might propose a more equitable split to ensure acceptance. Since the other person might be rational and prefer to have some money rather than none, I might propose a split where I keep most of the money but give a small portion to the other person to secure their acceptance. However, the optimal strategy is to propose a split that maximizes my own gain while ensuring the other person accepts. If the other person is rational, they would accept any amount greater than zero. Therefore, I would propose to keep $99 for myself and give $1 to the other person."
+8,qwen3,0.7,100,95,5,"As person A, I should propose a split that is fair enough to be accepted by person B. Since the total is $100, a 95-5 split is a common strategy in such experiments to leave a reasonable amount for myself while giving a small portion to the other person. This approach is intended to maximize my own gain while still providing enough incentive for the other person to accept the proposal."
+19,qwen3,0.7,100,95,5,"As person A, I propose to keep 95% of the $100 for myself and give 5% to person B. This is a common strategy in such experiments to maximize my own gain while still offering a small portion to ensure the proposal is accepted. Offering 5% is a reasonable compromise, as it's unlikely that person B would accept a lower amount, and it allows me to retain the majority of the funds."
+9,qwen3,0.7,100,90,10,"I would like to keep most of the money for myself while still offering a fair amount to the other person. By giving them $10, I ensure that they have a reasonable incentive to accept the proposal, as it's more than they would get if they rejected it. This way, I maximize my own gain while minimizing the risk of rejection."
+20,qwen3,0.7,100,90,10,"As the proposer, I aim to maximize my own benefit while still offering a reasonable amount to the other person to ensure acceptance. Splitting the money 90-10 is a common strategy in such scenarios, as it allows me to retain a significant portion while still providing a minimal share to the other person. This balance between self-interest and fairness is crucial to incentivize acceptance without over-giving."
+10,qwen3,0.7,100,99,1,"As Person A, I propose to keep $99 for myself and give $1 to Person B. This is a common strategy in such experiments to maximize my own gain while still offering a small amount to the other person, which might be accepted if they value fairness or the potential reward outweighs the risk of getting nothing."
+11,qwen3,0.7,100,50,50,"As person A, I believe it is fair to split the $100 evenly between myself and the other person. This ensures a balanced distribution and increases the likelihood of acceptance, as both parties would be satisfied with the equal division."
+21,qwen3,0.7,100,90,10,"As the proposer, I aim to maximize my own gain while still offering enough to the other person to ensure acceptance. Research suggests that proposals around 50-50 splits are more likely to be accepted, but since I am the proposer, I can propose a slightly less balanced split. Offering 90 for myself and 10 for the other person is a strategic move to keep my share high while still providing a reasonable amount to the other person to avoid rejection. If the other person accepts, I gain the majority; if they reject, both get nothing. Therefore, proposing 90-10 is a rational choice."
+12,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my own share while still offering a minimal amount to the other person to ensure acceptance. Offering $1 seems fair enough to keep the other person's acceptance, as they would prefer $1 over nothing."
+22,qwen3,0.7,100,90,10,"As the proposer, I believe it is fair to offer the other person a reasonable amount. Allocating $90 to myself and $10 to the other person seems justifiable, as it allows me to retain most of the money while still providing a portion to the other person. This approach balances self-interest with a degree of fairness."
+13,qwen3,0.7,100,90,10,"As the proposer, I believe it is fair to keep 90% of the $100 and offer 10% to the other person. This is because the proposer has the power to decide the division, and a 10% offer is typically accepted by the other party as it is better than nothing. By keeping 90%, I ensure that the proposal is accepted and the money is divided."
+23,qwen3,0.7,100,95,5,"As person A, I aim to propose a split that is fair and acceptable to both parties. By allocating $95 to myself and $5 to the other person, I ensure that the other person has an incentive to accept the proposal. This is because the other person would receive $5, which is better than the alternative of receiving $0 if they reject the proposal. Therefore, the other person is likely to accept my proposal, and both of us will benefit from the split."
+14,qwen3,0.7,100,95,5,"As the proposer, I should propose a split that is fair and likely to be accepted. Offering 5 to the other person is a common strategy in such games to ensure acceptance while keeping a large portion for myself."
+24,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my own gain while still offering enough to the other person to ensure acceptance. A 99-1 split is a common strategy in such scenarios, as it allows me to retain the majority of the funds while providing a minimal share to the other person, which is often accepted due to the potential for a larger reward if rejected."
+15,qwen3,0.7,100,95,5,"As the proposer, I aim to maximize my own benefit while still offering a reasonable share to the other person to ensure acceptance. A 5-95 split is a common strategy in such experiments to balance self-interest with the likelihood of the other person accepting the proposal."
+16,qwen3,0.7,100,99,1,"As person A, I propose to keep $99 for myself and give $1 to the other person. This is a common proposal in the ultimatum game where the proposer keeps most of the money, as it is believed that the responder may accept such a low offer due to the lack of alternative options. However, I acknowledge that the responder might reject this offer, resulting in both parties receiving nothing."
+25,qwen3,0.7,100,95,5,"As the proposer, I aim to maximize my own benefit while still offering enough to the other person to ensure acceptance. Research suggests that offers around 50-50 are more likely to be accepted, but since I'm the proposer, I can propose a slightly lower share for myself while still providing a fair amount to the other person. I believe 95-5 is a reasonable split that balances self-interest with the likelihood of acceptance."
+26,qwen3,0.7,100,90,10,"As the proposer, I aim to maximize my own gain while still offering a reasonable amount to the other person to ensure acceptance. Research suggests that offers around 50% are more likely to be accepted, but I'm proposing 90% for myself and 10% for the other person to test the limits of fairness and reciprocity."
+17,qwen3,0.7,100,99,1,"As the proposer, I want to maximize my own share while still offering enough to the other person to make the proposal acceptable. Offering a small amount to the other person (like $1) is a common strategy in these experiments to test fairness and rationality. I believe the other person will accept the offer, as the alternative is getting nothing. Therefore, I would propose keeping $99 for myself and giving $1 to the other person."
+18,qwen3,0.7,100,99,1,"As the proposer, I believe it's fair to keep most of the money while offering a small amount to the other person. This is a common strategy in such experiments to ensure at least some benefit to both parties while maximizing my own gain."
+27,qwen3,0.7,100,99,1,"As the proposer, I aim to maximize my share while ensuring the proposal is accepted. By offering the other person a minimal amount, I can retain a majority of the funds. The other person's acceptance is likely due to the alternative of receiving nothing, making a small token amount sufficient to secure agreement."
+19,qwen3,0.7,100,99,1,"As the proposer, I believe it's best to offer the other person a minimal amount to ensure my own gain while still meeting the minimum requirement for acceptance. Since the other person can either accept or reject, offering just $1 makes it more likely they'll accept, as rejecting would result in both getting nothing. This way, I maximize my share while still keeping the proposal viable."
+28,qwen3,0.7,100,75,25,"I propose to keep 75% of the money for myself and offer 25% to the other person. This is because I believe the proposer (person A) should maximize their own gain while still offering enough to the other person to ensure acceptance. Studies show that people often accept offers that are above 20% of the total, so offering 25% is a reasonable compromise."
+29,qwen3,0.7,100,95,5,"As the proposer, I want to maximize my own share while still offering enough to the other person to ensure acceptance. Since the other person could potentially reject the offer, I should offer them at least a minimal amount to avoid a zero outcome for both. Offering 5 dollars to the other person is a common practice in such situations to secure acceptance while keeping my share as high as possible."
+20,qwen3,0.7,100,90,10,"Since I'm person A, I can propose a split of the $100. To maximize my own gain while still making the proposal acceptable to person B, I should propose a split that gives me most of the money, but leaves a small portion for person B. This way, I can keep most of the money for myself, while still giving person B a reason to accept the offer, as they would get nothing if they reject it. This is a common strategy in such experiments to ensure that the proposer keeps as much as possible while still getting an acceptance from the other person."
+30,qwen3,0.7,100,99,1,"As person A, I propose to keep $99 for myself and give $1 to person B. This is because I believe person B will likely accept the proposal as it is significantly better than receiving nothing. I want to maximize my own gain while still providing a reasonable amount to person B to ensure acceptance."
+21,qwen3,0.7,100,99,1,"As person A, I propose to keep 99% of the $100 for myself and give 1% to the other person. This is because I have the power to decide the distribution, and it's in my best interest to maximize my own share while still offering a minimal amount to the other person to avoid rejection."
+22,qwen3,0.7,100,98,2,"As the proposer, I want to maximize my own gain while still offering enough to the other person to ensure they accept the proposal. Offering a small amount to the other person (e.g., $2) is sufficient to secure their acceptance, as the alternative is getting nothing if they reject the proposal. Therefore, I will propose keeping $98 for myself and giving $2 to the other person."
+23,qwen3,0.7,100,99,1,"As the proposer, I can set the terms. I will take 99 dollars for myself and give 1 dollar to the other person. This is a common strategy in such experiments to maximize personal gain while still offering a small amount to the other person to avoid rejection."
+24,qwen3,0.7,100,80,20,"As the proposer (Person A), I aim to maximize my own share while still offering enough to the other person (Person B) to make the proposal acceptable. Offering 80% to myself and 20% to the other is a common split in such experiments, as it balances self-interest with the possibility of acceptance. If I offer less than 20%, the other person may reject the proposal, resulting in both receiving nothing. By offering 20%, I increase the likelihood of acceptance while keeping a significant portion for myself."
+25,qwen3,0.7,100,95,5,"As the proposer, I aim to maximize my own gain while ensuring the proposal is acceptable to the other person. By offering a minimal share of $5 to the other person, I secure my own $95. This is a common strategy in such experiments where proposers typically keep most of the money and offer a minimal amount to the other person."
+26,qwen3,0.7,100,90,10,"As the proposer, I aim to maximize my own gain while still offering a fair share to the other person. A 90:10 split ensures I keep most of the money, but also leaves a small amount for the other person to maintain some level of fairness and increase the likelihood of acceptance."
+27,qwen3,0.7,100,100,0,"As the proposer, I believe it is in my best interest to keep all the money for myself. Since there is no guarantee that the other person will accept any proposal I make, I should take the risk of keeping everything for myself, rather than splitting it and potentially getting nothing if the other person rejects the proposal."
+28,qwen3,0.7,100,10,90,"As the proposer, I aim to maximize my own share while still offering enough to the other person to ensure acceptance. Based on typical behavior in such experiments, offering around 90% of the total to the other person and keeping 10% for myself is a common strategy to secure approval. This is because the other person is more likely to accept a generous offer, especially when they are aware that they could potentially receive nothing if they reject the proposal."
+29,qwen3,0.7,100,99,1,"As the proposer, I believe it's fair to keep most of the money while offering a minimal amount to the other person. This is because I have the power to determine the split, and the other person has no choice but to accept or reject. If they reject, both get nothing, so offering a small amount is a strategic move to ensure at least some reward."
+30,qwen3,0.7,100,99,1,"I propose to keep $99 for myself and give $1 to the other person. Since I am person A, I have the power to decide the distribution. My goal is to maximize my own profit while still providing a small token to the other person to ensure acceptance. The other person might accept this proposal as it is better than getting nothing if they reject it."
+1,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair approach, as it gives both parties an incentive to accept the proposal. If I were to propose a lopsided split in my favor, person B might reject the proposal out of spite or a sense of unfairness, leaving us both with nothing. By suggesting a 50-50 split, I aim to create a cooperative atmosphere and maximize our mutual gain."
+2,mixtral:8x7b,0.7,100,50,50,"I propose that we divide the money equally because this is a fair solution that maximizes the chance of person B accepting the proposal. By offering an even split, I minimize the risk of both of us receiving nothing if person B rejects an unequal offer."
+3,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an equal split of the money is the fairest way to approach this. By suggesting that we each receive $50, I am demonstrating a willingness to cooperate and share the wealth. This should increase the likelihood that person B will accept the proposal, as it is difficult to argue against an equal split without appearing greedy or unreasonable. If they do reject the proposal, then neither of us will receive any money, which would be unfortunate but ultimately a result of their decision."
+4,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an equal split of the $100 is the most fair and reasonable solution. This way, both person A and person B have a incentive to accept the proposal, as they will both receive a positive outcome. If I propose to take a larger share, then person B may reject the proposal out of fear of being taken advantage of, resulting in both of us receiving nothing. Therefore, an equal split is the most rational choice that maximizes the expected utility for both parties involved."
+5,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an even split of the $100 is the most fair and logical approach. This way, both person A and person B have a equal share in the money. By doing this, it also reduces the risk of person B rejecting the proposal, which would result in both parties receiving nothing. An even split will likely be accepted by person B, ensuring that we both receive $50."
+6,mixtral:8x7b,0.7,100,50,50,"As a fair and rational decision maker, I believe in the principle of equal distribution. Since the total amount to be divided is $100, and there are two individuals (including myself) involved in this economic experiment, it is only fair to divide the money equally, with each person receiving $50."
+7,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an equal split of the $100 is the most rational decision. This is because I want to maximize my own payout while also ensuring that person B has no incentive to reject the proposal. If I propose to take more than half of the money, person B would be at a loss if they accepted the proposal, making it likely that they would reject it, resulting in both of us receiving nothing. By proposing an equal split, I am providing a fair offer that aligns the interests of both parties, increasing the chances that person B will accept the proposal and we both receive a positive outcome."
+8,mixtral:8x7b,0.7,100,50,50,"As person A, I believe a fair proposal is to divide the $100 equally between myself and person B. This way, both parties benefit from the interaction and are incentivized to participate in future experiments. By proposing an even split, I aim to create a win-win situation that encourages cooperation and trust. This approach also reduces the risk of rejection by person B, as it demonstrates my intent to share the money fairly."
+9,mixtral:8x7b,0.7,100,50,50,"As a person A, I propose that we divide the money equally because this is a fair solution and it increases the chance that person B will accept the proposal. This way, both of us will receive $50, totaling to the initial sum of $100."
+10,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair approach. This way, both person A and person B have an incentive to accept the proposal, as they will both receive a significant amount of money. Additionally, by offering a fair split, I am building trust with person B, which can increase the likelihood of them accepting the proposal. If I were to propose a lopsided split in my favor, person B may reject the proposal out of spite or a desire for fairness, resulting in both of us receiving no money."
+11,mixtral:8x7b,0.7,100,50,50,"As a fair and rational person, I believe in equal distribution of resources. I propose that we divide the $100 sum equally, with $50 going to me and $50 going to the other person (person B). This way, both parties benefit from the transaction, and it encourages person B to accept the proposal. An equal split is a standard in many situations, and it fosters trust and cooperation between individuals. I believe that person B will also see the merit in this proposal and accept it, ensuring that we both receive a positive outcome."
+12,mixtral:8x7b,0.7,100,50,50,"As a fair and rational person, I think it's best to split the $100 evenly between myself and Person B. This way, both of us benefit from the experiment and there is no incentive for Person B to reject the proposal. A 50-50 split also aligns with the principle of fairness and equality, ensuring that neither party feels disadvantaged or cheated."
+13,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair solution. This way, both person A and person B have a equal share in the $100 and are incentivized to accept the proposal. If I were to propose a larger share for myself, person B may reject the proposal out of fear of being taken advantage of, resulting in both of us receiving nothing. By proposing an even split, I am maximizing the chances that person B will accept the proposal and we will both receive a positive outcome."
+14,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair option. This way, both person A and person B have a equal share and are incentivized to accept the proposal. If I were to propose a larger share for myself, person B may reject the proposal out of fairness, resulting in both of us receiving nothing. By proposing an even split, we both walk away with something, creating a win-win situation."
+15,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an equal split of $100 between myself and person B is the most rational decision. This is because it maximizes the potential gain for both parties, as any proposal that offers less than $50 to person B risks rejection, resulting in both of us receiving nothing. By suggesting a fair split, I aim to create a mutually beneficial situation and increase the likelihood of acceptance."
+16,mixtral:8x7b,0.7,100,50,50,"I believe that a fair proposal would be to split the money equally, with each person receiving $50. This way, both people benefit and have an incentive to accept the proposal. It also avoids the possibility of losing out on all the money if the other person rejects the proposal."
+17,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an equal split of the money is the most fair approach, as it gives both parties an incentive to accept the proposal. An unequal split may lead to the other person rejecting the proposal out of a sense of unfairness, in which case neither party would receive any money. By proposing an equal split, I maximize the chances that the other person will accept the proposal and we will both receive some money."
+18,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an equal split of the money is the most fair approach, as it gives both parties an incentive to accept the proposal. By suggesting a 50/50 split, I am maximizing the potential for a positive outcome for both myself and person B. This strategy fosters trust and cooperation, which are essential components of successful economic exchanges."
+19,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an equal split of $50 for myself and $50 for person B is the most rational decision. This offer is fair and provides a positive outcome for both parties involved. By offering an equal split, I maximize the chances of person B accepting the proposal, leading to a better outcome than if we both received nothing. Additionally, this strategy aligns with the principle of fairness, which can promote trust and cooperation between the two anonymous individuals in the experiment."
+20,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an even split of the $100 is the most rational decision. This is because I want to maximize my own payout while also ensuring that person B has no incentive to reject the proposal. If I propose any amount that is unevenly distributed in my favor, person B may reject the proposal out of spite or a desire for fairness, resulting in both of us receiving zero dollars. By proposing an even split, I minimize the risk of rejection and maximize the potential for mutual benefit."
+21,mixtral:8x7b,0.7,100,50,50,"I am proposing an even split of $100 because it is a fair division that incentivizes both person A and person B to accept the proposal. This way, we can both benefit from the allocation instead of risking to receive nothing if person B rejects the proposal."
+22,mixtral:8x7b,0.7,100,50,50,"As a person A, I believe that proposing an equal split of the $100 is the most rational decision. This is because I want to maximize my own earnings while also considering the fact that person B has the power to reject my proposal. By suggesting a fair split, I aim to increase the likelihood of person B accepting it, leading to a positive outcome for both of us. In contrast, if I propose an unfair amount for myself, person B may perceive this as greedy or unreasonable and choose to reject it, resulting in both of us receiving zero. Therefore, proposing a 50-50 split maximizes the potential benefit for both parties involved."
+23,mixtral:8x7b,0.7,100,50,50,"I believe that a fair proposal would be to split the money equally, giving $50 to each person. This way, both people in the pair receive a share of the money and neither person receives nothing. This proposal benefits both people and fosters a sense of fairness and cooperation."
+24,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair option. This way, both person A and person B have a equal share in the $100 and are incentivized to accept the proposal. If I were to propose a larger share for myself, person B may reject the proposal out of fear of being taken advantage of, resulting in both of us receiving nothing. By proposing an even split, I am maximizing the chances that person B will accept the proposal and we will both receive a positive outcome."
+25,mixtral:8x7b,0.7,100,50,50,"As a person A, I believe that proposing an equal split of $100 is the most rational decision. This is because the other person (person B) has the power to accept or reject the proposal. If I propose to give myself a larger share, person B may reject it, resulting in both of us receiving nothing. By proposing an equal split, I maximize the chances of person B accepting the proposal and thus securing a beneficial outcome for both of us."
+26,mixtral:8x7b,0.7,100,50,50,"As person A, I believe that proposing an even split of the $100 is the most rational choice. This is because I want to maximize my own payout while also ensuring that person B has no incentive to reject the proposal. If I propose a larger share for myself and a smaller share for person B, they may reject the proposal in hopes of getting a more favorable split if the proposal is resubmitted. However, if I propose an even split, person B has no reason to reject the proposal, as it offers them an equal chance to gain some money rather than none. Thus, I believe that proposing a 50-50 split is the best strategy to maximize my own payout while also ensuring a positive outcome for person B."
+27,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an equal split of the money is the most fair approach. This way, both person A and person B have a incentive to accept the proposal as they will both receive a significant amount of money. An unequal split may lead to person B rejecting the proposal out of spite or a sense of unfairness, resulting in both parties receiving nothing."
+28,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair approach, as it ensures that both parties receive a significant portion of the allocated sum. This also reduces the risk of the other party rejecting the proposal out of fear of being taken advantage of, which would result in both parties receiving nothing. By suggesting a 50-50 split, I aim to create a win-win situation for both myself and the anonymous person B."
+29,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an equal split of $100 is the most fair solution. This way, both person A and person B have a incentive to accept the proposal, as they will both receive a sum of money. If I were to propose a unequal split, person B might reject the proposal out of unfairness, resulting in both of us receiving nothing."
+30,mixtral:8x7b,0.7,100,50,50,"I believe that proposing an even split of the money is the most fair solution. This way, both person A and person B have a incentive to accept the proposal as they will both receive a positive amount of money. If I were to propose a uneven split, then person B may reject the proposal out of fear of being taken advantage of, resulting in both of us receiving nothing."
+1,llama3.3:latest,0.7,100,60,40,"As person A, I want to maximize my share while also considering the possibility that person B might reject my proposal if it's too unfair. Research in economics suggests that people tend to accept proposals that are not extremely uneven, often around a 60/40 or 70/30 split, as long as they feel it's somewhat reasonable and better than getting nothing. Proposing a 60/40 split allows me to get the larger share while also giving person B enough incentive (40% of $100 = $40) to accept the proposal rather than rejecting it and leaving both of us with no gain."
+2,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for person B. This division is based on the principle of fairness while also considering the strategic aspect of the game. By offering person B a significant share ($40), I am incentivizing them to accept the proposal, as receiving something is generally better than receiving nothing. At the same time, I am securing a larger share for myself, reflecting the advantage of being the proposer in this scenario."
+3,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for person B. This split is based on the principle of fairness while also considering the strategic aspect of the game. By offering person B $40, I am providing them with an incentive to accept the proposal since receiving $40 is better than receiving nothing if they reject it. However, I am also maximizing my own share by not offering too much, assuming that person B will be motivated by self-interest and accept a proposal that still benefits them, even if not equally."
+4,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for the other person. This decision is based on the principle of fairness, but also considering the potential risk of rejection. By offering $40 to the other person, I am providing them with an incentive to accept the proposal, as receiving $40 is better than receiving nothing if they reject it. However, I am also ensuring that I receive a larger share, as I am taking on the role of proposing the split. This split is not overly biased towards myself, which should reduce the likelihood of rejection by the other person."
+5,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I need to make a proposal that is reasonable enough for person B to accept. Research in economics has shown that people tend to reject proposals that are perceived as unfair, even if it means they receive nothing. Given this, I will propose a split of 60% for myself and 40% for person B, which is a relatively fair split considering I have the power to make the proposal, but still gives person B an incentive to accept."
+6,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, if person B rejects my proposal, we both receive zero. To minimize this risk, I will propose a split that is somewhat fair but still favors me, as I have the advantage of making the first move. Proposing a 60-40 split in my favor seems reasonable, as it gives person B an incentive to accept (they still receive $40), while also maximizing my own potential gain."
+7,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I need to make a proposal that is fair enough for person B to accept, but still favors me as the proposer. Research in economics suggests that people tend to reject offers that are perceived as unfair, with most people considering an offer of less than 30% of the total amount to be unfair. To minimize the risk of rejection and ensure I receive a significant portion of the money, I am proposing a split of $60 for myself and $40 for person B."
+8,llama3.3:latest,0.7,100,60,40,"As person A, I want to propose a division that is favorable to me but still acceptable to person B. Since person B has the power to reject the proposal and leave both of us with no gain, I need to make sure my offer is reasonable enough for them to accept. Proposing a 60-40 split in my favor allows me to gain a significant amount while also giving person B an incentive to accept, as receiving $40 is better than receiving nothing. This strategy balances self-interest with the necessity of ensuring cooperation from person B."
+9,llama3.3:latest,0.7,100,60,40,"As person A, I want to propose a division that is favorable to me but still acceptable to person B. Since person B has the power to reject the proposal and leave both of us with no money, I need to make sure my offer is reasonable enough for them to accept. Proposing a 60-40 split in my favor seems like a good balance between maximizing my gain and minimizing the risk of rejection by person B."
+10,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I need to balance my desire for a larger share with the risk of person B rejecting my proposal. Research in economics has shown that people tend to reject proposals that are perceived as unfair, even if it means they receive nothing. A common finding is that proposals where one person receives less than 30-40% of the total amount are often rejected. To minimize this risk and ensure that I receive some money, I am proposing a split of 60% for myself and 40% for person B. This split should be perceived as relatively fair, increasing the likelihood that person B will accept my proposal."
+11,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I want to make a proposal that is generous enough to persuade person B to accept it, but not so generous that I give up too much of the $100. Research in economics suggests that people tend to be fair and cooperative, but also sensitive to unfairness. A common finding in similar experiments, known as the Ultimatum Game, is that proposals that offer around 40% to the responder (person B) and keep around 60% for the proposer (me) have a relatively high acceptance rate. Proposals that are too skewed towards the proposer tend to be rejected. Therefore, I propose a division of $60 for myself and $40 for person B, hoping it will be perceived as fair enough to be accepted."
+12,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. Since person B has the option to reject my proposal if they feel it's unfair, I need to balance my desire for a larger share with the risk of getting nothing if person B rejects it. Research from similar experiments, such as the Ultimatum Game, suggests that proposals which are perceived as overly unfair (e.g., offering less than 20-30% to the other person) are more likely to be rejected. Therefore, proposing a split where I get $60 and the other person gets $40 seems like a reasonable compromise: it gives me a larger share while also being fair enough that person B might accept it, as it's still better for them than receiving nothing."
+13,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, if person B rejects my proposal, we both receive zero. Therefore, I want to make a proposal that is reasonable enough for person B to accept, but still gives me the majority of the money. Research in economics has shown that people tend to reject proposals that are perceived as unfair, even if it means they receive nothing. A common benchmark for fairness in such experiments is around 50/50 or slightly uneven distributions where one party gets a bit more due to their role (in this case, making the proposal). Given I have the power to propose and want to ensure acceptance, proposing a 60/40 split seems like a reasonable strategy. It acknowledges person B's contribution to the potential acceptance of the deal while also rewarding me for taking on the proposer's role and the risk that comes with it."
+14,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for the other person. This split is based on the idea that as the proposer, I have the power to make the initial offer, but I also need to consider the possibility that the other person may reject my proposal if they feel it is not fair. By offering $40 to the other person, I am providing them with a reasonable incentive to accept the proposal, while still maximizing my own share. This approach takes into account the principles of game theory and the concept of fairness in economic transactions."
+15,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for the other person. This decision is based on the principle of fairness while also considering the strategic aspect of the game. Since the other person has the power to accept or reject my proposal, I need to make sure they have an incentive to accept it. By offering them $40, which is a significant portion of the total amount, I am hoping to make the proposal attractive enough for them to accept, thus ensuring that both of us receive some money rather than risking getting nothing if they reject the offer."
+16,llama3.3:latest,0.7,100,60,40,"As person A, I want to maximize my share while still making the proposal attractive enough for person B to accept. Since the alternative to accepting is getting zero, I'm assuming person B will accept as long as they get a reasonable amount. Offering $40 to person B (or 40% of the total) seems like a fair split considering the power dynamic in this experiment, where I have the initial proposal power and they have the final acceptance or rejection power. This split also acknowledges that person B has some bargaining power through their ability to reject the offer, which would leave both of us with nothing."
+17,llama3.3:latest,0.7,100,60,40,"As person A, I want to maximize my share while also considering the possibility that person B might reject my proposal if it's too unfair. Research in economics, such as the Ultimatum Game, suggests that people tend to reject offers they perceive as unfair, even if it means they receive nothing. A common finding is that offers below 30-40% of the total amount are often rejected. Therefore, I'm proposing a split where I get $60 and person B gets $40, hoping this will be perceived as fair enough for them to accept, while still maximizing my own gain."
+18,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for person B. This split is based on the idea that as the proposer, I have more power in the negotiation, but I still need to make sure person B has enough incentive to accept the proposal. If person B rejects the proposal, we both get zero, which is a worse outcome for both of us. By offering $40, I am providing a significant enough share to make acceptance attractive, while also maximizing my own gain."
+19,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. Since person B has the option to reject my proposal if they feel it's unfair, I need to balance my desire for a larger share with the risk of getting nothing if person B rejects my offer. Research in economics, such as the ultimatum game, suggests that people are more likely to accept proposals that seem fair or reasonable, even if they're not perfectly equal. Proposing a 60:40 split leans towards favoring myself but still offers person B enough (40%) that they might consider it a better option than receiving nothing. This strategy aims to maximize my gain while minimizing the risk of rejection."
+20,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we both receive zero. This creates an incentive for me to propose a division that is fair enough for person B to accept, while still maximizing my own share. Research in economics, particularly in the ultimatum game (which this experiment resembles), suggests that proposals that are perceived as unfair are often rejected, even if rejecting means receiving no money at all. A common finding is that people tend to accept offers of 40% or more of the total amount but reject offers below 20-30%. Therefore, proposing a 60/40 split balances my desire for a larger share with the need to make the proposal acceptable to person B."
+21,llama3.3:latest,0.7,100,60,40,"I'm proposing a split where I receive $60 and the other person receives $40. This decision is based on the principle of self-interest, aiming to maximize my own gain while still offering enough to the other person to make acceptance more likely than rejection. Since the alternative to accepting this proposal is receiving nothing, I'm betting that the other person will find $40 preferable to $0, even if they might have preferred a more equal split."
+22,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for the other person. This split is not extremely uneven, which might provoke a rejection from the other person due to fairness concerns. By offering $40, I'm providing an incentive for the other person to accept, as receiving something is generally better than receiving nothing. However, I'm also aiming to maximize my own share by not being too generous, assuming that the other person will prioritize gaining some money over rejecting the proposal out of principle."
+23,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I need to balance my desire for a larger share with the risk of person B rejecting my proposal. Research in economics has shown that people tend to reject proposals that are perceived as unfair or overly biased towards one party. Given this, I am proposing a 60-40 split, which is somewhat generous but still favors me as the proposer. This split should be enough to incentivize person B to accept the proposal, while also maximizing my own share."
+24,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero. Therefore, I want to make a proposal that is fair enough to be accepted by person B, but still gives me a larger share of the money. Research in economics has shown that people tend to reject proposals that they perceive as unfair, even if it means they receive nothing. A common finding is that proposals where one person receives more than 70-80% of the total amount are often rejected. Given this, I propose a split of $60 for myself and $40 for person B, which should be seen as relatively fair while still favoring me."
+25,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we will both receive zero dollars. Therefore, I want to make a proposal that is generous enough to incentivize person B to accept, but still allows me to receive a significant share of the money. Research in economics has shown that people tend to be loss-averse and prefer fair outcomes. Given this, proposing a 60-40 split may be seen as more acceptable than a highly unequal split like 90-10 or 95-5, which might prompt person B to reject the proposal due to feeling treated unfairly. A 50-50 split would be perfectly fair but offering slightly less to myself and more to person B (than an extremely skewed offer) increases the likelihood of acceptance while still benefiting me substantially."
+26,llama3.3:latest,0.7,100,60,40,"Proposing a 60-40 split to balance between maximizing my share and ensuring the proposal is perceived as fair enough by person B to be accepted, avoiding a rejection that would result in zero payout for both parties."
+27,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that person B has the power to reject my proposal if they feel it is unfair. In order to maximize my chances of getting a positive outcome, I will propose a split that is somewhat generous to person B, but still favors me as the proposer. A 60-40 split in my favor seems like a reasonable compromise, as it acknowledges the importance of person B's acceptance while also rewarding me for taking the initiative. This split is also consistent with typical outcomes observed in ultimatum game experiments, where proposers tend to offer around 40% of the total amount to the responder."
+28,llama3.3:latest,0.7,100,60,40,"I am proposing a split of $60 for myself and $40 for the other person. This split is not overly greedy, as it still offers the other person a significant amount of money, but it also reflects the fact that I have the power to make the proposal and they have to accept or reject it. If the other person rejects the proposal, we both get nothing, which would be an unfavorable outcome for both of us. By offering $40, I am providing an incentive for the other person to accept the proposal, while also maximizing my own share."
+29,llama3.3:latest,0.7,100,60,40,"As person A, I have the power to make the initial proposal. However, I also know that if person B rejects my proposal, we both receive zero. This creates an incentive for me to propose a division that person B will accept. Since person B's identity and characteristics are unknown, I will rely on general principles of fairness and self-interest. A common finding in ultimatum game experiments like this is that proposals which offer less than 20-30% of the total amount to the responder (person B) are often rejected, as responders tend to perceive such offers as unfair. To minimize the risk of rejection and ensure that both parties receive some money, I will propose a split that leans towards fairness but still favors me slightly, as I have the advantage of making the first offer."
+30,llama3.3:latest,0.7,100,60,40,"As person A, I want to propose a division that is favorable to me but still acceptable to person B. Since person B has the power to reject the proposal and leave both of us with no gain, I need to offer them enough to make acceptance more appealing than rejection. Offering $40 to person B (and thus keeping $60 for myself) seems like a reasonable compromise. It gives person B an incentive to accept, as they receive a significant amount, while also allowing me to keep the larger share."
+1,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split to ensure fairness and mutual benefit, considering game theory principles where both parties are rational and self-interested."
+2,deepseek-r1:7b,0.7,100,50,50,"I will offer a 50-50 split. Since rejecting any proposal results in both parties receiving nothing, accepting this split ensures mutual benefit and maximizes my share."
+3,deepseek-r1:7b,0.7,100,50,50,"Since both parties are rational and self-interested, offering an equal split ensures that my partner receives a fair amount rather than nothing. This minimizes my risk of rejection while providing a balanced division."
+4,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split of $50 each. This is fair and ensures acceptance."
+5,deepseek-r1:7b,0.7,100,90,10,"I propose taking 90% ($90) for myself and offering 10% ($10) to my partner. This balance is based on the understanding that a fair offer, albeit minimal, will likely be accepted by my partner to avoid receiving nothing."
+6,deepseek-r1:7b,0.7,100,30,70,"I propose splitting the $100 into a $30 share for myself and $70 for the other person. This offer is designed to be fair yet self-serving, considering potential social norms of fairness in decision-making."
+7,deepseek-r1:7b,0.7,100,50,50,"I propose splitting the $100 equally, offering $50 to me and $50 to person B. This is a fair division that avoids any risk of rejection leading to both receiving nothing."
+8,deepseek-r1:7b,0.7,100,10,90,"I propose a split where I receive $10, which is 10% of the total. This seems like a reasonable offer that acknowledges fairness while allowing me to retain most of the amount if rejected."
+9,deepseek-r1:7b,0.7,100,99,1,"As a rational player, I will propose to take the majority share while offering the smallest possible amount to the other person. This ensures that their alternative (rejection) yields nothing, making them accept the proposal."
+10,deepseek-r1:7b,0.7,100,51,49,"I choose to offer myself 51% and the other participant 49%. This balance slightly favors me while maintaining fairness, reducing the risk of rejection by ensuring both parties receive a reasonable share."
+11,deepseek-r1:7b,0.7,100,60,40,"I propose an unequal split, giving myself 60% ($60) and offering 40% ($40) to the other person. This approach balances fairness with self-interest, ensuring a mutually acceptable division without risking rejection."
+12,deepseek-r1:7b,0.7,100,90,10,"I propose keeping $90 for myself and offering $10 to the other person. This ensures they receive a positive amount, making it more likely they will accept my proposal rather than risk getting nothing."
+13,deepseek-r1:7b,0.7,100,70,30,"Proposing a 50-50 split ensures fairness and minimizes the risk of rejection. This division is equitable and reflects mutual benefit, increasing the likelihood that B will accept the proposal."
+14,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split of $50 each. This is a fair and predictable offer that aligns with the principle of fairness, making it likely to be accepted without introducing unnecessary risks."
+15,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split to ensure fairness and reduce the risk of rejection."
+16,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split, giving me $50 and offering $50 to the other person. This is based on the assumption that fairness is more appealing for both parties rather than risking getting nothing."
+17,deepseek-r1:7b,0.7,100,50,50,"Since B has no alternative but to accept any positive amount offered by me (as rejecting would result in both of us receiving nothing), the fairest and most straightforward proposal is a 50-50 split. This ensures that B receives an equal share without any loss, while I receive half as well."
+18,deepseek-r1:7b,0.7,100,50,50,"As a rational participant, I would propose an equal split. Person B will accept this proposal since receiving $50 is better than rejecting it and getting nothing."
+19,deepseek-r1:7b,0.7,100,50,50,"In game theory scenarios like the ultimatum game, fairness often plays a role. By offering an equal split of $50 each, I ensure that my proposal is accepted, maximizing my share while respecting the other party's potential preference for fairness over rejection."
+20,deepseek-r1:7b,0.7,100,50,50,"As a rational player, I offer an equal split of $50 each. This ensures fairness and respects the rational choice where accepting is better than rejecting."
+21,deepseek-r1:7b,0.7,100,98,2,"As Person A, I propose splitting the $100 such that I take $98 and offer $2 to Person B. This is a minimal positive amount, ensuring my proposal will be accepted by Person B since they prefer a small gain over nothing."
+22,deepseek-r1:7b,0.7,100,80,20,"I propose a division where I receive $80 and the other person receives $20. This split is intended to offer a reasonable yet fair portion, ensuring that their share is significant enough to accept rather than risk receiving nothing."
+23,deepseek-r1:7b,0.7,100,50,50,"I propose a fair split where I take half of the total amount, which is $50. This ensures that Person B receives an equal share and there's no perceived unfairness or risk of rejection."
+24,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split of $50 each. This is because in the absence of information about B's alternative offers, and considering that rejecting my proposal would result in both parties receiving nothing, a fair and balanced approach ensures both parties have an incentive to accept the offer."
+25,deepseek-r1:7b,0.7,100,99,1,"I propose taking $99 for myself and offering $1 to the other person. This ensures that the other person receives a minimal amount, which is better than nothing if they reject my proposal. Since accepting this offer yields them $1 rather than $0, it's in their best interest to accept, making it mutually beneficial."
+26,deepseek-r1:7b,0.7,100,50,50,"I propose an equal split of 50-50. This demonstrates a basic understanding of fairness and shows that I value equality while protecting my own interest."
+27,deepseek-r1:7b,0.7,100,90,10,"I propose a division where I receive $90 and person B receives $10. This ensures that person B prefers accepting the offer (receiving at least some amount) rather than rejecting it, which would result in both receiving nothing."
+28,deepseek-r1:7b,0.7,100,99,1,"As person A, I should propose a split that ensures person B accepts the offer. Since any positive amount is better than zero for B, offering them just $1 allows me to keep the remaining $99 while ensuring acceptance."
+29,deepseek-r1:7b,0.7,100,99,1,"I should propose a split that gives me as much as possible while ensuring the other person accepts. Offering them just $1 ensures they prefer accepting over rejecting."
+30,deepseek-r1:7b,0.7,100,50,50,"I propose a fair division where both parties receive $50 each. This split is based on the principle of equality and self-interest, ensuring that neither party feels exploited while maintaining symmetry."
+1,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I offered a distribution that favors me slightly but is still fair enough to likely be accepted by the other person."
+2,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"To benefit myself while also offering a fair share to encourage acceptance."
+3,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"An even split increases the likelihood of acceptance and ensures fairness."
+4,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Offering $60 to myself and $40 to person B, aiming for fairness to encourage acceptance."
+5,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"This division seems fair, ensuring acceptance by the other party."
+6,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"Offering an equal share encourages fairness and increases the likelihood of the partner accepting my proposal."
+7,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"Splitting evenly seems fair and maximizes the chance of acceptance."
+8,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose to offer 40% to encourage acceptance and ensure a fair distribution, although keeping a slightly larger share for myself."
+9,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose 60-40 as it provides me with a slight advantage while still being fair enough to encourage acceptance."
+10,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Offering 60 to myself and 40 to the other person provides me with a larger share while maintaining fairness that might encourage acceptance."
+11,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I propose keeping $60 and offering $40 to Person B, aiming to secure acceptance from both sides."
+12,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose a fair division where I receive slightly more to reflect my proposing role, but still fair enough to be likely accepted."
+13,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose a division that favors me slightly while still being appealing to person B, hoping they'll accept it."
+14,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose this division to benefit myself more while still making the offer appealing enough to be accepted by person B."
+15,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I proposed 60 for myself and 40 for the other person, balancing fairness and self-interest."
+16,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose a division that slightly favors me while remaining fair enough to encourage acceptance."
+17,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I propose a split of 60-40 to maximize my share while still providing enough incentive to the other person to accept."
+18,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"Offering an equal split increases fairness and the likelihood the proposal will be accepted."
+19,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose a 60-40 split to appear fair enough for person B to accept, while ensuring I gain an advantageous share."
+20,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I chose an amount reasonable enough to ensure the other person would accept it, securing a beneficial outcome for both of us."
+21,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"I chose an equal split of $50 for each person, as this is fair and maximizes the chance of acceptance."
+22,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"A fair split ensures both parties are satisfied and maximizes acceptance likelihood."
+23,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Offering $40 to the other person seems fair and likely to be accepted."
+24,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Proposing a fair split increases acceptance chances and ensures mutual benefit."
+25,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I'll take slightly more than half while still providing a fair share to encourage acceptance."
+26,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I propose a split favoring myself slightly, anticipating that the other person will still accept a fair enough deal."
+27,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Offering a higher but fair amount to ensure the proposal is accepted."
+28,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"I believe a 60-40 split is fair enough to entice person B to accept, giving me a slightly higher share."
+29,gpt-4.5-preview-2025-02-27,0.7,100,60,40,"Allocating 60 to myself, 40 to the other person, to seem fair and ensure acceptance."
+30,gpt-4.5-preview-2025-02-27,0.7,100,50,50,"Splitting evenly is fair and increases acceptance probability."
diff --git a/figures/ultimatum/proposer_violin.svg b/figures/ultimatum/proposer_violin.svg
new file mode 100644
index 0000000..e569dd5
--- /dev/null
+++ b/figures/ultimatum/proposer_violin.svg
@@ -0,0 +1,3246 @@
+<?xml version="1.0" encoding="utf-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg xmlns:xlink="http://www.w3.org/1999/xlink" width="864pt" height="432pt" viewBox="0 0 864 432" xmlns="http://www.w3.org/2000/svg" version="1.1">
+ <metadata>
+ <rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+ <cc:Work>
+ <dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
+ <dc:date>2025-05-12T11:26:46.122087</dc:date>
+ <dc:format>image/svg+xml</dc:format>
+ <dc:creator>
+ <cc:Agent>
+ <dc:title>Matplotlib v3.10.1, https://matplotlib.org/</dc:title>
+ </cc:Agent>
+ </dc:creator>
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <defs>
+ <style type="text/css">*{stroke-linejoin: round; stroke-linecap: butt}</style>
+ </defs>
+ <g id="figure_1">
+ <g id="patch_1">
+ <path d="M 0 432
+L 864 432
+L 864 0
+L 0 0
+z
+" style="fill: #ffffff"/>
+ </g>
+ <g id="axes_1">
+ <g id="patch_2">
+ <path d="M 108 384.48
+L 777.6 384.48
+L 777.6 51.84
+L 108 51.84
+z
+" style="fill: #ffffff"/>
+ </g>
+ <g id="FillBetweenPolyCollection_1">
+ <defs>
+ <path id="m091da8df1f" d="M 151.498544 -198.684268
+L 148.201456 -198.684268
+L 147.903974 -199.326444
+L 147.56925 -199.968621
+L 147.196079 -200.610797
+L 146.783949 -201.252973
+L 146.333166 -201.89515
+L 145.844973 -202.537326
+L 145.321648 -203.179503
+L 144.766579 -203.821679
+L 144.184306 -204.463855
+L 143.580523 -205.106032
+L 142.962038 -205.748208
+L 142.33669 -206.390385
+L 141.713208 -207.032561
+L 141.101041 -207.674737
+L 140.510126 -208.316914
+L 139.950638 -208.95909
+L 139.4327 -209.601267
+L 138.966084 -210.243443
+L 138.559904 -210.88562
+L 138.222316 -211.527796
+L 137.960249 -212.169972
+L 137.779157 -212.812149
+L 137.68283 -213.454325
+L 137.673249 -214.096502
+L 137.75051 -214.738678
+L 137.912806 -215.380854
+L 138.156482 -216.023031
+L 138.476137 -216.665207
+L 138.8648 -217.307384
+L 139.314131 -217.94956
+L 139.814669 -218.591736
+L 140.356099 -219.233913
+L 140.92752 -219.876089
+L 141.517713 -220.518266
+L 142.115388 -221.160442
+L 142.709406 -221.802618
+L 143.288953 -222.444795
+L 143.843684 -223.086971
+L 144.36381 -223.729148
+L 144.840151 -224.371324
+L 145.264135 -225.013501
+L 145.627773 -225.655677
+L 145.923602 -226.297853
+L 146.144615 -226.94003
+L 146.284185 -227.582206
+L 146.336003 -228.224383
+L 146.294029 -228.866559
+L 146.152483 -229.508735
+L 145.905872 -230.150912
+L 145.549072 -230.793088
+L 145.077449 -231.435265
+L 144.487053 -232.077441
+L 143.774839 -232.719617
+L 142.93895 -233.361794
+L 141.979015 -234.00397
+L 140.896474 -234.646147
+L 139.694897 -235.288323
+L 138.380275 -235.930499
+L 136.961282 -236.572676
+L 135.449456 -237.214852
+L 133.859304 -237.857029
+L 132.2083 -238.499205
+L 130.516766 -239.141382
+L 128.807628 -239.783558
+L 127.106039 -240.425734
+L 125.438879 -241.067911
+L 123.834143 -241.710087
+L 122.320234 -242.352264
+L 120.925178 -242.99444
+L 119.67581 -243.636616
+L 118.596948 -244.278793
+L 117.710598 -244.920969
+L 117.035227 -245.563146
+L 116.585144 -246.205322
+L 116.37 -246.847498
+L 116.39446 -247.489675
+L 116.658039 -248.131851
+L 117.155124 -248.774028
+L 117.875177 -249.416204
+L 118.803111 -250.05838
+L 119.919814 -250.700557
+L 121.20281 -251.342733
+L 122.627006 -251.98491
+L 124.16551 -252.627086
+L 125.790467 -253.269263
+L 127.47389 -253.911439
+L 129.188439 -254.553615
+L 130.908132 -255.195792
+L 132.608954 -255.837968
+L 134.269351 -256.480145
+L 135.870598 -257.122321
+L 137.397035 -257.764497
+L 138.836178 -258.406674
+L 140.178709 -259.04885
+L 141.418361 -259.691027
+L 142.551718 -260.333203
+L 143.577937 -260.975379
+L 144.498429 -261.617556
+L 145.316503 -262.259732
+L 154.383497 -262.259732
+L 154.383497 -262.259732
+L 155.201571 -261.617556
+L 156.122063 -260.975379
+L 157.148282 -260.333203
+L 158.281639 -259.691027
+L 159.521291 -259.04885
+L 160.863822 -258.406674
+L 162.302965 -257.764497
+L 163.829402 -257.122321
+L 165.430649 -256.480145
+L 167.091046 -255.837968
+L 168.791868 -255.195792
+L 170.511561 -254.553615
+L 172.22611 -253.911439
+L 173.909533 -253.269263
+L 175.53449 -252.627086
+L 177.072994 -251.98491
+L 178.49719 -251.342733
+L 179.780186 -250.700557
+L 180.896889 -250.05838
+L 181.824823 -249.416204
+L 182.544876 -248.774028
+L 183.041961 -248.131851
+L 183.30554 -247.489675
+L 183.33 -246.847498
+L 183.114856 -246.205322
+L 182.664773 -245.563146
+L 181.989402 -244.920969
+L 181.103052 -244.278793
+L 180.02419 -243.636616
+L 178.774822 -242.99444
+L 177.379766 -242.352264
+L 175.865857 -241.710087
+L 174.261121 -241.067911
+L 172.593961 -240.425734
+L 170.892372 -239.783558
+L 169.183234 -239.141382
+L 167.4917 -238.499205
+L 165.840696 -237.857029
+L 164.250544 -237.214852
+L 162.738718 -236.572676
+L 161.319725 -235.930499
+L 160.005103 -235.288323
+L 158.803526 -234.646147
+L 157.720985 -234.00397
+L 156.76105 -233.361794
+L 155.925161 -232.719617
+L 155.212947 -232.077441
+L 154.622551 -231.435265
+L 154.150928 -230.793088
+L 153.794128 -230.150912
+L 153.547517 -229.508735
+L 153.405971 -228.866559
+L 153.363997 -228.224383
+L 153.415815 -227.582206
+L 153.555385 -226.94003
+L 153.776398 -226.297853
+L 154.072227 -225.655677
+L 154.435865 -225.013501
+L 154.859849 -224.371324
+L 155.33619 -223.729148
+L 155.856316 -223.086971
+L 156.411047 -222.444795
+L 156.990594 -221.802618
+L 157.584612 -221.160442
+L 158.182287 -220.518266
+L 158.77248 -219.876089
+L 159.343901 -219.233913
+L 159.885331 -218.591736
+L 160.385869 -217.94956
+L 160.8352 -217.307384
+L 161.223863 -216.665207
+L 161.543518 -216.023031
+L 161.787194 -215.380854
+L 161.94949 -214.738678
+L 162.026751 -214.096502
+L 162.01717 -213.454325
+L 161.920843 -212.812149
+L 161.739751 -212.169972
+L 161.477684 -211.527796
+L 161.140096 -210.88562
+L 160.733916 -210.243443
+L 160.2673 -209.601267
+L 159.749362 -208.95909
+L 159.189874 -208.316914
+L 158.598959 -207.674737
+L 157.986792 -207.032561
+L 157.36331 -206.390385
+L 156.737962 -205.748208
+L 156.119477 -205.106032
+L 155.515694 -204.463855
+L 154.933421 -203.821679
+L 154.378352 -203.179503
+L 153.855027 -202.537326
+L 153.366834 -201.89515
+L 152.916051 -201.252973
+L 152.503921 -200.610797
+L 152.13075 -199.968621
+L 151.796026 -199.326444
+L 151.498544 -198.684268
+z
+" style="stroke: #1f1f1f; stroke-width: 1.25"/>
+ </defs>
+ <g clip-path="url(#p229f3ceefe)">
+ <use xlink:href="#m091da8df1f" x="0" y="432" style="fill: #8bbbee; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ </g>
+ <g id="FillBetweenPolyCollection_2">
+ <path d="M 233.779264 477.329048
+L 233.320736 477.329048
+L 233.257361 472.093309
+L 233.180567 466.857571
+L 233.088697 461.621833
+L 232.980196 456.386094
+L 232.853702 451.150356
+L 232.708139 445.914618
+L 232.542823 440.678879
+L 232.357553 435.443141
+L 232.1527 430.207403
+L 231.929276 424.971664
+L 231.688974 419.735926
+L 231.434184 414.500188
+L 231.167965 409.264449
+L 230.893982 404.028711
+L 230.616395 398.792973
+L 230.339717 393.557234
+L 230.068629 388.321496
+L 229.807771 383.085758
+L 229.561507 377.850019
+L 229.333692 372.614281
+L 229.127428 367.378543
+L 228.944842 362.142804
+L 228.78689 356.907066
+L 228.653199 351.671328
+L 228.541946 346.435589
+L 228.449805 341.199851
+L 228.37195 335.964113
+L 228.302121 330.728374
+L 228.232772 325.492636
+L 228.15528 320.256898
+L 228.06024 315.021159
+L 227.937828 309.785421
+L 227.778223 304.549683
+L 227.5721 299.313944
+L 227.31115 294.078206
+L 226.988625 288.842468
+L 226.599879 283.606729
+L 226.14286 278.370991
+L 225.618533 273.135253
+L 225.031183 267.899514
+L 224.388569 262.663776
+L 223.701898 257.428038
+L 222.985589 252.192299
+L 222.256828 246.956561
+L 221.534913 241.720823
+L 220.840403 236.485084
+L 220.194118 231.249346
+L 219.616032 226.013608
+L 219.124112 220.777869
+L 218.733184 215.542131
+L 218.453884 210.306392
+L 218.291755 205.070654
+L 218.246558 199.834916
+L 218.311835 194.599177
+L 218.474763 189.363439
+L 218.716316 184.127701
+L 219.011744 178.891962
+L 219.331356 173.656224
+L 219.641594 168.420486
+L 219.90636 163.184747
+L 220.088565 157.949009
+L 220.151843 152.713271
+L 220.062365 147.477532
+L 219.790705 142.241794
+L 219.313651 137.006056
+L 218.6159 131.770317
+L 217.691514 126.534579
+L 216.54506 121.298841
+L 215.192321 116.063102
+L 213.660488 110.827364
+L 211.98777 105.591626
+L 210.222367 100.355887
+L 208.420811 95.120149
+L 206.645706 89.884411
+L 204.962959 84.648672
+L 203.438653 79.412934
+L 202.135718 74.177196
+L 201.11064 68.941457
+L 200.41042 63.705719
+L 200.07 58.469981
+L 200.110371 53.234242
+L 200.537483 47.998504
+L 201.342068 42.762766
+L 202.500363 37.527027
+L 203.975698 32.291289
+L 205.720793 27.055551
+L 207.680586 21.819812
+L 209.795383 16.584074
+L 212.004058 11.348336
+L 214.247111 6.112597
+L 216.469354 0.876859
+L 218.622089 -4.358879
+L 220.664665 -9.594618
+L 222.56539 -14.830356
+L 224.3018 -20.066094
+L 225.860368 -25.301833
+L 227.235738 -30.537571
+L 228.429624 -35.773309
+L 229.449495 -41.009048
+L 237.650505 -41.009048
+L 237.650505 -41.009048
+L 238.670376 -35.773309
+L 239.864262 -30.537571
+L 241.239632 -25.301833
+L 242.7982 -20.066094
+L 244.53461 -14.830356
+L 246.435335 -9.594618
+L 248.477911 -4.358879
+L 250.630646 0.876859
+L 252.852889 6.112597
+L 255.095942 11.348336
+L 257.304617 16.584074
+L 259.419414 21.819812
+L 261.379207 27.055551
+L 263.124302 32.291289
+L 264.599637 37.527027
+L 265.757932 42.762766
+L 266.562517 47.998504
+L 266.989629 53.234242
+L 267.03 58.469981
+L 266.68958 63.705719
+L 265.98936 68.941457
+L 264.964282 74.177196
+L 263.661347 79.412934
+L 262.137041 84.648672
+L 260.454294 89.884411
+L 258.679189 95.120149
+L 256.877633 100.355887
+L 255.11223 105.591626
+L 253.439512 110.827364
+L 251.907679 116.063102
+L 250.55494 121.298841
+L 249.408486 126.534579
+L 248.4841 131.770317
+L 247.786349 137.006056
+L 247.309295 142.241794
+L 247.037635 147.477532
+L 246.948157 152.713271
+L 247.011435 157.949009
+L 247.19364 163.184747
+L 247.458406 168.420486
+L 247.768644 173.656224
+L 248.088256 178.891962
+L 248.383684 184.127701
+L 248.625237 189.363439
+L 248.788165 194.599177
+L 248.853442 199.834916
+L 248.808245 205.070654
+L 248.646116 210.306392
+L 248.366816 215.542131
+L 247.975888 220.777869
+L 247.483968 226.013608
+L 246.905882 231.249346
+L 246.259597 236.485084
+L 245.565087 241.720823
+L 244.843172 246.956561
+L 244.114411 252.192299
+L 243.398102 257.428038
+L 242.711431 262.663776
+L 242.068817 267.899514
+L 241.481467 273.135253
+L 240.95714 278.370991
+L 240.500121 283.606729
+L 240.111375 288.842468
+L 239.78885 294.078206
+L 239.5279 299.313944
+L 239.321777 304.549683
+L 239.162172 309.785421
+L 239.03976 315.021159
+L 238.94472 320.256898
+L 238.867228 325.492636
+L 238.797879 330.728374
+L 238.72805 335.964113
+L 238.650195 341.199851
+L 238.558054 346.435589
+L 238.446801 351.671328
+L 238.31311 356.907066
+L 238.155158 362.142804
+L 237.972572 367.378543
+L 237.766308 372.614281
+L 237.538493 377.850019
+L 237.292229 383.085758
+L 237.031371 388.321496
+L 236.760283 393.557234
+L 236.483605 398.792973
+L 236.206018 404.028711
+L 235.932035 409.264449
+L 235.665816 414.500188
+L 235.411026 419.735926
+L 235.170724 424.971664
+L 234.9473 430.207403
+L 234.742447 435.443141
+L 234.557177 440.678879
+L 234.391861 445.914618
+L 234.246298 451.150356
+L 234.119804 456.386094
+L 234.011303 461.621833
+L 233.919433 466.857571
+L 233.842639 472.093309
+L 233.779264 477.329048
+z
+" clip-path="url(#p229f3ceefe)" style="fill: #409884; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="FillBetweenPolyCollection_3">
+ <defs>
+ <path id="m3b45145cca" d="M 401.166392 -133.970897
+L 400.733608 -133.970897
+L 400.656428 -136.760414
+L 400.554724 -139.549931
+L 400.421739 -142.339448
+L 400.249237 -145.128966
+L 400.027338 -147.918483
+L 399.74441 -150.708
+L 399.387042 -153.497517
+L 398.940157 -156.287035
+L 398.3873 -159.076552
+L 397.711142 -161.866069
+L 396.894237 -164.655586
+L 395.92005 -167.445104
+L 394.774237 -170.234621
+L 393.446145 -173.024138
+L 391.930444 -175.813655
+L 390.228772 -178.603173
+L 388.351241 -181.39269
+L 386.317635 -184.182207
+L 384.158108 -186.971724
+L 381.913233 -189.761242
+L 379.63326 -192.550759
+L 377.376547 -195.340276
+L 375.20716 -198.129793
+L 373.191764 -200.91931
+L 371.396004 -203.708828
+L 369.880646 -206.498345
+L 368.697791 -209.287862
+L 367.887515 -212.077379
+L 367.475226 -214.866897
+L 367.47 -217.656414
+L 367.864057 -220.445931
+L 368.633409 -223.235448
+L 369.739615 -226.024966
+L 371.132473 -228.814483
+L 372.753366 -231.604
+L 374.53897 -234.393517
+L 376.424984 -237.183035
+L 378.349584 -239.972552
+L 380.256359 -242.762069
+L 382.096548 -245.551586
+L 383.830504 -248.341103
+L 385.428377 -251.130621
+L 386.870076 -253.920138
+L 388.144646 -256.709655
+L 389.249196 -259.499172
+L 390.187547 -262.28869
+L 390.96874 -265.078207
+L 391.605549 -267.867724
+L 392.113088 -270.657241
+L 392.507588 -273.446759
+L 392.805385 -276.236276
+L 393.022131 -279.025793
+L 393.17223 -281.81531
+L 393.268478 -284.604828
+L 393.321876 -287.394345
+L 393.341587 -290.183862
+L 393.335012 -292.973379
+L 393.307936 -295.762897
+L 393.264736 -298.552414
+L 393.208618 -301.341931
+L 393.141874 -304.131448
+L 393.06614 -306.920965
+L 392.982665 -309.710483
+L 392.892564 -312.5
+L 392.797074 -315.289517
+L 392.697786 -318.079034
+L 392.59686 -320.868552
+L 392.497195 -323.658069
+L 392.402541 -326.447586
+L 392.317542 -329.237103
+L 392.247686 -332.026621
+L 392.199153 -334.816138
+L 392.178567 -337.605655
+L 392.192655 -340.395172
+L 392.247844 -343.18469
+L 392.349813 -345.974207
+L 392.503056 -348.763724
+L 392.710485 -351.553241
+L 392.97312 -354.342758
+L 393.289888 -357.132276
+L 393.657573 -359.921793
+L 394.070905 -362.71131
+L 394.52279 -365.500827
+L 395.004667 -368.290345
+L 395.506953 -371.079862
+L 396.019548 -373.869379
+L 396.532341 -376.658896
+L 397.035707 -379.448414
+L 397.520928 -382.237931
+L 397.980538 -385.027448
+L 398.408553 -387.816965
+L 398.800598 -390.606483
+L 399.153926 -393.396
+L 399.467336 -396.185517
+L 399.74102 -398.975034
+L 399.976351 -401.764552
+L 400.175635 -404.554069
+L 400.34186 -407.343586
+L 400.478444 -410.133103
+L 401.421556 -410.133103
+L 401.421556 -410.133103
+L 401.55814 -407.343586
+L 401.724365 -404.554069
+L 401.923649 -401.764552
+L 402.15898 -398.975034
+L 402.432664 -396.185517
+L 402.746074 -393.396
+L 403.099402 -390.606483
+L 403.491447 -387.816965
+L 403.919462 -385.027448
+L 404.379072 -382.237931
+L 404.864293 -379.448414
+L 405.367659 -376.658896
+L 405.880452 -373.869379
+L 406.393047 -371.079862
+L 406.895333 -368.290345
+L 407.37721 -365.500827
+L 407.829095 -362.71131
+L 408.242427 -359.921793
+L 408.610112 -357.132276
+L 408.92688 -354.342758
+L 409.189515 -351.553241
+L 409.396944 -348.763724
+L 409.550187 -345.974207
+L 409.652156 -343.18469
+L 409.707345 -340.395172
+L 409.721433 -337.605655
+L 409.700847 -334.816138
+L 409.652314 -332.026621
+L 409.582458 -329.237103
+L 409.497459 -326.447586
+L 409.402805 -323.658069
+L 409.30314 -320.868552
+L 409.202214 -318.079034
+L 409.102926 -315.289517
+L 409.007436 -312.5
+L 408.917335 -309.710483
+L 408.83386 -306.920965
+L 408.758126 -304.131448
+L 408.691382 -301.341931
+L 408.635264 -298.552414
+L 408.592064 -295.762897
+L 408.564988 -292.973379
+L 408.558413 -290.183862
+L 408.578124 -287.394345
+L 408.631522 -284.604828
+L 408.72777 -281.81531
+L 408.877869 -279.025793
+L 409.094615 -276.236276
+L 409.392412 -273.446759
+L 409.786912 -270.657241
+L 410.294451 -267.867724
+L 410.93126 -265.078207
+L 411.712453 -262.28869
+L 412.650804 -259.499172
+L 413.755354 -256.709655
+L 415.029924 -253.920138
+L 416.471623 -251.130621
+L 418.069496 -248.341103
+L 419.803452 -245.551586
+L 421.643641 -242.762069
+L 423.550416 -239.972552
+L 425.475016 -237.183035
+L 427.36103 -234.393517
+L 429.146634 -231.604
+L 430.767527 -228.814483
+L 432.160385 -226.024966
+L 433.266591 -223.235448
+L 434.035943 -220.445931
+L 434.43 -217.656414
+L 434.424774 -214.866897
+L 434.012485 -212.077379
+L 433.202209 -209.287862
+L 432.019354 -206.498345
+L 430.503996 -203.708828
+L 428.708236 -200.91931
+L 426.69284 -198.129793
+L 424.523453 -195.340276
+L 422.26674 -192.550759
+L 419.986767 -189.761242
+L 417.741892 -186.971724
+L 415.582365 -184.182207
+L 413.548759 -181.39269
+L 411.671228 -178.603173
+L 409.969556 -175.813655
+L 408.453855 -173.024138
+L 407.125763 -170.234621
+L 405.97995 -167.445104
+L 405.005763 -164.655586
+L 404.188858 -161.866069
+L 403.5127 -159.076552
+L 402.959843 -156.287035
+L 402.512958 -153.497517
+L 402.15559 -150.708
+L 401.872662 -147.918483
+L 401.650763 -145.128966
+L 401.478261 -142.339448
+L 401.345276 -139.549931
+L 401.243572 -136.760414
+L 401.166392 -133.970897
+z
+" style="stroke: #1f1f1f; stroke-width: 1.25"/>
+ </defs>
+ <g clip-path="url(#p229f3ceefe)">
+ <use xlink:href="#m3b45145cca" x="0" y="432" style="fill: #e77759; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ </g>
+ <g id="FillBetweenPolyCollection_4">
+ <defs>
+ <path id="mda3f9fabe2" d="M 489.181025 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 451.17 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 464.343354 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 480.118975 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 518.13 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 504.956646 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+L 489.181025 -213.84
+z
+" style="stroke: #1f1f1f; stroke-width: 1.25"/>
+ </defs>
+ <g clip-path="url(#p229f3ceefe)">
+ <use xlink:href="#mda3f9fabe2" x="0" y="432" style="fill: #d69e35; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ </g>
+ <g id="FillBetweenPolyCollection_5">
+ <path d="M 572.848119 455.412673
+L 563.851881 455.412673
+L 562.509322 450.61969
+L 560.903214 445.826706
+L 559.027136 441.033723
+L 556.889415 436.24074
+L 554.516118 431.447756
+L 551.952979 426.654773
+L 549.265773 421.86179
+L 546.538788 417.068806
+L 543.871212 412.275823
+L 541.371521 407.48284
+L 539.150224 402.689857
+L 537.311601 397.896873
+L 535.945259 393.10389
+L 535.118441 388.310907
+L 534.87 383.517923
+L 535.206762 378.72494
+L 536.102762 373.931957
+L 537.50145 369.138974
+L 539.320609 364.34599
+L 541.459409 359.553007
+L 543.806752 354.760024
+L 546.249982 349.96704
+L 548.68303 345.174057
+L 551.013228 340.381074
+L 553.166236 335.588091
+L 555.088836 330.795107
+L 556.749576 326.002124
+L 558.137541 321.209141
+L 559.259643 316.416157
+L 560.136931 311.623174
+L 560.800439 306.830191
+L 561.287026 302.037208
+L 561.63557 297.244224
+L 561.883778 292.451241
+L 562.065753 287.658258
+L 562.210368 282.865274
+L 562.340419 278.072291
+L 562.472453 273.279308
+L 562.617168 268.486325
+L 562.780222 263.693341
+L 562.9633 258.900358
+L 563.165287 254.107375
+L 563.383413 249.314391
+L 563.614241 244.521408
+L 563.854443 239.728425
+L 564.101279 234.935442
+L 564.352813 230.142458
+L 564.607872 225.349475
+L 564.865812 220.556492
+L 565.126189 215.763508
+L 565.388393 210.970525
+L 565.651342 206.177542
+L 565.913276 201.384558
+L 566.171695 196.591575
+L 566.423422 191.798592
+L 566.664792 187.005609
+L 566.891899 182.212625
+L 567.100884 177.419642
+L 567.288189 172.626659
+L 567.450775 167.833675
+L 567.586252 163.040692
+L 567.692947 158.247709
+L 567.769899 153.454726
+L 567.816817 148.661742
+L 567.834017 143.868759
+L 567.822367 139.075776
+L 567.783246 134.282792
+L 567.718541 129.489809
+L 567.630668 124.696826
+L 567.522609 119.903843
+L 567.39795 115.110859
+L 567.260893 110.317876
+L 567.116232 105.524893
+L 566.969271 100.731909
+L 566.82567 95.938926
+L 566.691237 91.145943
+L 566.571661 86.35296
+L 566.472209 81.559976
+L 566.397421 76.766993
+L 566.350822 71.97401
+L 566.334691 67.181026
+L 566.349902 62.388043
+L 566.395867 57.59506
+L 566.470583 52.802077
+L 566.570777 48.009093
+L 566.692149 43.21611
+L 566.829675 38.423127
+L 566.977952 33.630143
+L 567.131547 28.83716
+L 567.285322 24.044177
+L 567.434707 19.251194
+L 567.575899 14.45821
+L 567.705991 9.665227
+L 567.823005 4.872244
+L 567.925866 0.07926
+L 568.014303 -4.713723
+L 568.088722 -9.506706
+L 568.150043 -14.29969
+L 568.199543 -19.092673
+L 568.500457 -19.092673
+L 568.500457 -19.092673
+L 568.549957 -14.29969
+L 568.611278 -9.506706
+L 568.685697 -4.713723
+L 568.774134 0.07926
+L 568.876995 4.872244
+L 568.994009 9.665227
+L 569.124101 14.45821
+L 569.265293 19.251194
+L 569.414678 24.044177
+L 569.568453 28.83716
+L 569.722048 33.630143
+L 569.870325 38.423127
+L 570.007851 43.21611
+L 570.129223 48.009093
+L 570.229417 52.802077
+L 570.304133 57.59506
+L 570.350098 62.388043
+L 570.365309 67.181026
+L 570.349178 71.97401
+L 570.302579 76.766993
+L 570.227791 81.559976
+L 570.128339 86.35296
+L 570.008763 91.145943
+L 569.87433 95.938926
+L 569.730729 100.731909
+L 569.583768 105.524893
+L 569.439107 110.317876
+L 569.30205 115.110859
+L 569.177391 119.903843
+L 569.069332 124.696826
+L 568.981459 129.489809
+L 568.916754 134.282792
+L 568.877633 139.075776
+L 568.865983 143.868759
+L 568.883183 148.661742
+L 568.930101 153.454726
+L 569.007053 158.247709
+L 569.113748 163.040692
+L 569.249225 167.833675
+L 569.411811 172.626659
+L 569.599116 177.419642
+L 569.808101 182.212625
+L 570.035208 187.005609
+L 570.276578 191.798592
+L 570.528305 196.591575
+L 570.786724 201.384558
+L 571.048658 206.177542
+L 571.311607 210.970525
+L 571.573811 215.763508
+L 571.834188 220.556492
+L 572.092128 225.349475
+L 572.347187 230.142458
+L 572.598721 234.935442
+L 572.845557 239.728425
+L 573.085759 244.521408
+L 573.316587 249.314391
+L 573.534713 254.107375
+L 573.7367 258.900358
+L 573.919778 263.693341
+L 574.082832 268.486325
+L 574.227547 273.279308
+L 574.359581 278.072291
+L 574.489632 282.865274
+L 574.634247 287.658258
+L 574.816222 292.451241
+L 575.06443 297.244224
+L 575.412974 302.037208
+L 575.899561 306.830191
+L 576.563069 311.623174
+L 577.440357 316.416157
+L 578.562459 321.209141
+L 579.950424 326.002124
+L 581.611164 330.795107
+L 583.533764 335.588091
+L 585.686772 340.381074
+L 588.01697 345.174057
+L 590.450018 349.96704
+L 592.893248 354.760024
+L 595.240591 359.553007
+L 597.379391 364.34599
+L 599.19855 369.138974
+L 600.597238 373.931957
+L 601.493238 378.72494
+L 601.83 383.517923
+L 601.581559 388.310907
+L 600.754741 393.10389
+L 599.388399 397.896873
+L 597.549776 402.689857
+L 595.328479 407.48284
+L 592.828788 412.275823
+L 590.161212 417.068806
+L 587.434227 421.86179
+L 584.747021 426.654773
+L 582.183882 431.447756
+L 579.810585 436.24074
+L 577.672864 441.033723
+L 575.796786 445.826706
+L 574.190678 450.61969
+L 572.848119 455.412673
+z
+" clip-path="url(#p229f3ceefe)" style="fill: #6b72da; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="FillBetweenPolyCollection_6">
+ <path d="M 652.300586 429.539179
+L 651.799414 429.539179
+L 651.735098 424.966493
+L 651.659483 420.393807
+L 651.572042 415.82112
+L 651.47261 411.248434
+L 651.361449 406.675747
+L 651.239301 402.103061
+L 651.107403 397.530374
+L 650.967466 392.957688
+L 650.821605 388.385001
+L 650.672226 383.812315
+L 650.521857 379.239628
+L 650.372947 374.666942
+L 650.227625 370.094256
+L 650.08744 365.521569
+L 649.953101 360.948883
+L 649.824212 356.376196
+L 649.699039 351.80351
+L 649.574294 347.230823
+L 649.444964 342.658137
+L 649.304179 338.08545
+L 649.143121 333.512764
+L 648.950995 328.940077
+L 648.715056 324.367391
+L 648.420721 319.794705
+L 648.051782 315.222018
+L 647.590762 310.649332
+L 647.019428 306.076645
+L 646.319512 301.503959
+L 645.473648 296.931272
+L 644.466524 292.358586
+L 643.286233 287.785899
+L 641.92576 283.213213
+L 640.384503 278.640526
+L 638.669708 274.06784
+L 636.797665 269.495154
+L 634.794489 264.922467
+L 632.696343 260.349781
+L 630.548961 255.777094
+L 628.406407 251.204408
+L 626.329048 246.631721
+L 624.380826 242.059035
+L 622.62596 237.486348
+L 621.125336 232.913662
+L 619.932829 228.340975
+L 619.091888 223.768289
+L 618.632673 219.195603
+L 618.57 214.622916
+L 618.902296 210.05023
+L 619.611633 205.477543
+L 620.664863 200.904857
+L 622.015713 196.33217
+L 623.607663 191.759484
+L 625.377334 187.186797
+L 627.258098 182.614111
+L 629.183606 178.041425
+L 631.090991 173.468738
+L 632.923526 168.896052
+L 634.632616 164.323365
+L 636.179072 159.750679
+L 637.533682 155.177992
+L 638.677161 150.605306
+L 639.599618 146.032619
+L 640.299659 141.459933
+L 640.783299 136.887246
+L 641.062798 132.31456
+L 641.155522 127.741874
+L 641.082904 123.169187
+L 640.86952 118.596501
+L 640.542299 114.023814
+L 640.129815 109.451128
+L 639.66164 104.878441
+L 639.167712 100.305755
+L 638.677665 95.733068
+L 638.22012 91.160382
+L 637.821918 86.587695
+L 637.507315 82.015009
+L 637.297177 77.442323
+L 637.208226 72.869636
+L 637.252398 68.29695
+L 637.436366 63.724263
+L 637.761294 59.151577
+L 638.222842 54.57889
+L 638.811462 50.006204
+L 639.512959 45.433517
+L 640.309295 40.860831
+L 641.179593 36.288144
+L 642.101247 31.715458
+L 643.051093 27.142772
+L 644.006531 22.570085
+L 644.946542 17.997399
+L 645.852525 13.424712
+L 646.708928 8.852026
+L 647.503624 4.279339
+L 648.228064 -0.293347
+L 648.877189 -4.866034
+L 649.449169 -9.43872
+L 649.94499 -14.011407
+L 650.367945 -18.584093
+L 650.723088 -23.156779
+L 653.376912 -23.156779
+L 653.376912 -23.156779
+L 653.732055 -18.584093
+L 654.15501 -14.011407
+L 654.650831 -9.43872
+L 655.222811 -4.866034
+L 655.871936 -0.293347
+L 656.596376 4.279339
+L 657.391072 8.852026
+L 658.247475 13.424712
+L 659.153458 17.997399
+L 660.093469 22.570085
+L 661.048907 27.142772
+L 661.998753 31.715458
+L 662.920407 36.288144
+L 663.790705 40.860831
+L 664.587041 45.433517
+L 665.288538 50.006204
+L 665.877158 54.57889
+L 666.338706 59.151577
+L 666.663634 63.724263
+L 666.847602 68.29695
+L 666.891774 72.869636
+L 666.802823 77.442323
+L 666.592685 82.015009
+L 666.278082 86.587695
+L 665.87988 91.160382
+L 665.422335 95.733068
+L 664.932288 100.305755
+L 664.43836 104.878441
+L 663.970185 109.451128
+L 663.557701 114.023814
+L 663.23048 118.596501
+L 663.017096 123.169187
+L 662.944478 127.741874
+L 663.037202 132.31456
+L 663.316701 136.887246
+L 663.800341 141.459933
+L 664.500382 146.032619
+L 665.422839 150.605306
+L 666.566318 155.177992
+L 667.920928 159.750679
+L 669.467384 164.323365
+L 671.176474 168.896052
+L 673.009009 173.468738
+L 674.916394 178.041425
+L 676.841902 182.614111
+L 678.722666 187.186797
+L 680.492337 191.759484
+L 682.084287 196.33217
+L 683.435137 200.904857
+L 684.488367 205.477543
+L 685.197704 210.05023
+L 685.53 214.622916
+L 685.467327 219.195603
+L 685.008112 223.768289
+L 684.167171 228.340975
+L 682.974664 232.913662
+L 681.47404 237.486348
+L 679.719174 242.059035
+L 677.770952 246.631721
+L 675.693593 251.204408
+L 673.551039 255.777094
+L 671.403657 260.349781
+L 669.305511 264.922467
+L 667.302335 269.495154
+L 665.430292 274.06784
+L 663.715497 278.640526
+L 662.17424 283.213213
+L 660.813767 287.785899
+L 659.633476 292.358586
+L 658.626352 296.931272
+L 657.780488 301.503959
+L 657.080572 306.076645
+L 656.509238 310.649332
+L 656.048218 315.222018
+L 655.679279 319.794705
+L 655.384944 324.367391
+L 655.149005 328.940077
+L 654.956879 333.512764
+L 654.795821 338.08545
+L 654.655036 342.658137
+L 654.525706 347.230823
+L 654.400961 351.80351
+L 654.275788 356.376196
+L 654.146899 360.948883
+L 654.01256 365.521569
+L 653.872375 370.094256
+L 653.727053 374.666942
+L 653.578143 379.239628
+L 653.427774 383.812315
+L 653.278395 388.385001
+L 653.132534 392.957688
+L 652.992597 397.530374
+L 652.860699 402.103061
+L 652.738551 406.675747
+L 652.62739 411.248434
+L 652.527958 415.82112
+L 652.440517 420.393807
+L 652.364902 424.966493
+L 652.300586 429.539179
+z
+" clip-path="url(#p229f3ceefe)" style="fill: #a38cee; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="FillBetweenPolyCollection_7">
+ <path d="M 736.130154 463.732022
+L 735.369846 463.732022
+L 735.263787 458.770971
+L 735.137582 453.80992
+L 734.9903 448.84887
+L 734.821831 443.887819
+L 734.633081 438.926768
+L 734.426121 433.965717
+L 734.204284 429.004666
+L 733.972163 424.043615
+L 733.735524 419.082564
+L 733.501102 414.121513
+L 733.276302 409.160462
+L 733.068816 404.199411
+L 732.886178 399.23836
+L 732.735304 394.277309
+L 732.62205 389.316258
+L 732.550823 384.355207
+L 732.524298 379.394156
+L 732.543241 374.433105
+L 732.606487 369.472054
+L 732.711033 364.511003
+L 732.852268 359.549952
+L 733.024298 354.588901
+L 733.220325 349.62785
+L 733.43307 344.666799
+L 733.655174 339.705748
+L 733.879567 334.744697
+L 734.099769 329.783647
+L 734.310115 324.822596
+L 734.505891 319.861545
+L 734.683392 314.900494
+L 734.839912 309.939443
+L 734.973674 304.978392
+L 735.083729 300.017341
+L 735.169829 295.05629
+L 735.232308 290.095239
+L 735.271961 285.134188
+L 735.289951 280.173137
+L 735.287731 275.212086
+L 735.266985 270.251035
+L 735.229592 265.289984
+L 735.177592 260.328933
+L 735.113151 255.367882
+L 735.038516 250.406831
+L 734.955957 245.44578
+L 734.867674 240.484729
+L 734.775684 235.523678
+L 734.681673 230.562627
+L 734.586818 225.601576
+L 734.491587 220.640525
+L 734.395517 215.679475
+L 734.296977 210.718424
+L 734.192935 205.757373
+L 734.078726 200.796322
+L 733.947838 195.835271
+L 733.791737 190.87422
+L 733.599741 185.913169
+L 733.358978 180.952118
+L 733.05444 175.991067
+L 732.669186 171.030016
+L 732.184711 166.068965
+L 731.581534 161.107914
+L 730.840016 156.146863
+L 729.941436 151.185812
+L 728.869312 146.224761
+L 727.610933 141.26371
+L 726.159038 136.302659
+L 724.513528 131.341608
+L 722.68308 126.380557
+L 720.686488 121.419506
+L 718.553547 116.458455
+L 716.325324 111.497404
+L 714.053641 106.536353
+L 711.799697 101.575303
+L 709.631808 96.614252
+L 707.622315 91.653201
+L 705.84384 86.69215
+L 704.36513 81.731099
+L 703.246812 76.770048
+L 702.537412 71.808997
+L 702.27 66.847946
+L 702.45978 61.886895
+L 703.10287 56.925844
+L 704.176402 51.964793
+L 705.639948 47.003742
+L 707.438145 42.042691
+L 709.504286 37.08164
+L 711.764547 32.120589
+L 714.142462 27.159538
+L 716.563285 22.198487
+L 718.957872 17.237436
+L 721.26582 12.276385
+L 723.437685 7.315334
+L 725.436191 2.354283
+L 727.236483 -2.606768
+L 728.825511 -7.567819
+L 730.200749 -12.52887
+L 731.368435 -17.48992
+L 732.341577 -22.450971
+L 733.137904 -27.412022
+L 738.362096 -27.412022
+L 738.362096 -27.412022
+L 739.158423 -22.450971
+L 740.131565 -17.48992
+L 741.299251 -12.52887
+L 742.674489 -7.567819
+L 744.263517 -2.606768
+L 746.063809 2.354283
+L 748.062315 7.315334
+L 750.23418 12.276385
+L 752.542128 17.237436
+L 754.936715 22.198487
+L 757.357538 27.159538
+L 759.735453 32.120589
+L 761.995714 37.08164
+L 764.061855 42.042691
+L 765.860052 47.003742
+L 767.323598 51.964793
+L 768.39713 56.925844
+L 769.04022 61.886895
+L 769.23 66.847946
+L 768.962588 71.808997
+L 768.253188 76.770048
+L 767.13487 81.731099
+L 765.65616 86.69215
+L 763.877685 91.653201
+L 761.868192 96.614252
+L 759.700303 101.575303
+L 757.446359 106.536353
+L 755.174676 111.497404
+L 752.946453 116.458455
+L 750.813512 121.419506
+L 748.81692 126.380557
+L 746.986472 131.341608
+L 745.340962 136.302659
+L 743.889067 141.26371
+L 742.630688 146.224761
+L 741.558564 151.185812
+L 740.659984 156.146863
+L 739.918466 161.107914
+L 739.315289 166.068965
+L 738.830814 171.030016
+L 738.44556 175.991067
+L 738.141022 180.952118
+L 737.900259 185.913169
+L 737.708263 190.87422
+L 737.552162 195.835271
+L 737.421274 200.796322
+L 737.307065 205.757373
+L 737.203023 210.718424
+L 737.104483 215.679475
+L 737.008413 220.640525
+L 736.913182 225.601576
+L 736.818327 230.562627
+L 736.724316 235.523678
+L 736.632326 240.484729
+L 736.544043 245.44578
+L 736.461484 250.406831
+L 736.386849 255.367882
+L 736.322408 260.328933
+L 736.270408 265.289984
+L 736.233015 270.251035
+L 736.212269 275.212086
+L 736.210049 280.173137
+L 736.228039 285.134188
+L 736.267692 290.095239
+L 736.330171 295.05629
+L 736.416271 300.017341
+L 736.526326 304.978392
+L 736.660088 309.939443
+L 736.816608 314.900494
+L 736.994109 319.861545
+L 737.189885 324.822596
+L 737.400231 329.783647
+L 737.620433 334.744697
+L 737.844826 339.705748
+L 738.06693 344.666799
+L 738.279675 349.62785
+L 738.475702 354.588901
+L 738.647732 359.549952
+L 738.788967 364.511003
+L 738.893513 369.472054
+L 738.956759 374.433105
+L 738.975702 379.394156
+L 738.949177 384.355207
+L 738.87795 389.316258
+L 738.764696 394.277309
+L 738.613822 399.23836
+L 738.431184 404.199411
+L 738.223698 409.160462
+L 737.998898 414.121513
+L 737.764476 419.082564
+L 737.527837 424.043615
+L 737.295716 429.004666
+L 737.073879 433.965717
+L 736.866919 438.926768
+L 736.678169 443.887819
+L 736.5097 448.84887
+L 736.362418 453.80992
+L 736.236213 458.770971
+L 736.130154 463.732022
+z
+" clip-path="url(#p229f3ceefe)" style="fill: #ad3c4f; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="matplotlib.axis_1">
+ <g id="xtick_1">
+ <g id="line2d_1">
+ <defs>
+ <path id="m1ed00a0df3" d="M 0 0
+L 0 3.5
+" style="stroke: #000000; stroke-width: 0.8"/>
+ </defs>
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="149.85" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_1">
+ <!-- gpt-4.5-preview-2025-02-27 -->
+ <g transform="translate(79.4125 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-67" d="M 2906 1791
+Q 2906 2416 2648 2759
+Q 2391 3103 1925 3103
+Q 1463 3103 1205 2759
+Q 947 2416 947 1791
+Q 947 1169 1205 825
+Q 1463 481 1925 481
+Q 2391 481 2648 825
+Q 2906 1169 2906 1791
+z
+M 3481 434
+Q 3481 -459 3084 -895
+Q 2688 -1331 1869 -1331
+Q 1566 -1331 1297 -1286
+Q 1028 -1241 775 -1147
+L 775 -588
+Q 1028 -725 1275 -790
+Q 1522 -856 1778 -856
+Q 2344 -856 2625 -561
+Q 2906 -266 2906 331
+L 2906 616
+Q 2728 306 2450 153
+Q 2172 0 1784 0
+Q 1141 0 747 490
+Q 353 981 353 1791
+Q 353 2603 747 3093
+Q 1141 3584 1784 3584
+Q 2172 3584 2450 3431
+Q 2728 3278 2906 2969
+L 2906 3500
+L 3481 3500
+L 3481 434
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-70" d="M 1159 525
+L 1159 -1331
+L 581 -1331
+L 581 3500
+L 1159 3500
+L 1159 2969
+Q 1341 3281 1617 3432
+Q 1894 3584 2278 3584
+Q 2916 3584 3314 3078
+Q 3713 2572 3713 1747
+Q 3713 922 3314 415
+Q 2916 -91 2278 -91
+Q 1894 -91 1617 61
+Q 1341 213 1159 525
+z
+M 3116 1747
+Q 3116 2381 2855 2742
+Q 2594 3103 2138 3103
+Q 1681 3103 1420 2742
+Q 1159 2381 1159 1747
+Q 1159 1113 1420 752
+Q 1681 391 2138 391
+Q 2594 391 2855 752
+Q 3116 1113 3116 1747
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-74" d="M 1172 4494
+L 1172 3500
+L 2356 3500
+L 2356 3053
+L 1172 3053
+L 1172 1153
+Q 1172 725 1289 603
+Q 1406 481 1766 481
+L 2356 481
+L 2356 0
+L 1766 0
+Q 1100 0 847 248
+Q 594 497 594 1153
+L 594 3053
+L 172 3053
+L 172 3500
+L 594 3500
+L 594 4494
+L 1172 4494
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-2d" d="M 313 2009
+L 1997 2009
+L 1997 1497
+L 313 1497
+L 313 2009
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-34" d="M 2419 4116
+L 825 1625
+L 2419 1625
+L 2419 4116
+z
+M 2253 4666
+L 3047 4666
+L 3047 1625
+L 3713 1625
+L 3713 1100
+L 3047 1100
+L 3047 0
+L 2419 0
+L 2419 1100
+L 313 1100
+L 313 1709
+L 2253 4666
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-2e" d="M 684 794
+L 1344 794
+L 1344 0
+L 684 0
+L 684 794
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-35" d="M 691 4666
+L 3169 4666
+L 3169 4134
+L 1269 4134
+L 1269 2991
+Q 1406 3038 1543 3061
+Q 1681 3084 1819 3084
+Q 2600 3084 3056 2656
+Q 3513 2228 3513 1497
+Q 3513 744 3044 326
+Q 2575 -91 1722 -91
+Q 1428 -91 1123 -41
+Q 819 9 494 109
+L 494 744
+Q 775 591 1075 516
+Q 1375 441 1709 441
+Q 2250 441 2565 725
+Q 2881 1009 2881 1497
+Q 2881 1984 2565 2268
+Q 2250 2553 1709 2553
+Q 1456 2553 1204 2497
+Q 953 2441 691 2322
+L 691 4666
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-72" d="M 2631 2963
+Q 2534 3019 2420 3045
+Q 2306 3072 2169 3072
+Q 1681 3072 1420 2755
+Q 1159 2438 1159 1844
+L 1159 0
+L 581 0
+L 581 3500
+L 1159 3500
+L 1159 2956
+Q 1341 3275 1631 3429
+Q 1922 3584 2338 3584
+Q 2397 3584 2469 3576
+Q 2541 3569 2628 3553
+L 2631 2963
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-65" d="M 3597 1894
+L 3597 1613
+L 953 1613
+Q 991 1019 1311 708
+Q 1631 397 2203 397
+Q 2534 397 2845 478
+Q 3156 559 3463 722
+L 3463 178
+Q 3153 47 2828 -22
+Q 2503 -91 2169 -91
+Q 1331 -91 842 396
+Q 353 884 353 1716
+Q 353 2575 817 3079
+Q 1281 3584 2069 3584
+Q 2775 3584 3186 3129
+Q 3597 2675 3597 1894
+z
+M 3022 2063
+Q 3016 2534 2758 2815
+Q 2500 3097 2075 3097
+Q 1594 3097 1305 2825
+Q 1016 2553 972 2059
+L 3022 2063
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-76" d="M 191 3500
+L 800 3500
+L 1894 563
+L 2988 3500
+L 3597 3500
+L 2284 0
+L 1503 0
+L 191 3500
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-69" d="M 603 3500
+L 1178 3500
+L 1178 0
+L 603 0
+L 603 3500
+z
+M 603 4863
+L 1178 4863
+L 1178 4134
+L 603 4134
+L 603 4863
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-77" d="M 269 3500
+L 844 3500
+L 1563 769
+L 2278 3500
+L 2956 3500
+L 3675 769
+L 4391 3500
+L 4966 3500
+L 4050 0
+L 3372 0
+L 2619 2869
+L 1863 0
+L 1184 0
+L 269 3500
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-32" d="M 1228 531
+L 3431 531
+L 3431 0
+L 469 0
+L 469 531
+Q 828 903 1448 1529
+Q 2069 2156 2228 2338
+Q 2531 2678 2651 2914
+Q 2772 3150 2772 3378
+Q 2772 3750 2511 3984
+Q 2250 4219 1831 4219
+Q 1534 4219 1204 4116
+Q 875 4013 500 3803
+L 500 4441
+Q 881 4594 1212 4672
+Q 1544 4750 1819 4750
+Q 2544 4750 2975 4387
+Q 3406 4025 3406 3419
+Q 3406 3131 3298 2873
+Q 3191 2616 2906 2266
+Q 2828 2175 2409 1742
+Q 1991 1309 1228 531
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-30" d="M 2034 4250
+Q 1547 4250 1301 3770
+Q 1056 3291 1056 2328
+Q 1056 1369 1301 889
+Q 1547 409 2034 409
+Q 2525 409 2770 889
+Q 3016 1369 3016 2328
+Q 3016 3291 2770 3770
+Q 2525 4250 2034 4250
+z
+M 2034 4750
+Q 2819 4750 3233 4129
+Q 3647 3509 3647 2328
+Q 3647 1150 3233 529
+Q 2819 -91 2034 -91
+Q 1250 -91 836 529
+Q 422 1150 422 2328
+Q 422 3509 836 4129
+Q 1250 4750 2034 4750
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-37" d="M 525 4666
+L 3525 4666
+L 3525 4397
+L 1831 0
+L 1172 0
+L 2766 4134
+L 525 4134
+L 525 4666
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-67"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(126.953125 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(166.162109 0)"/>
+ <use xlink:href="#DejaVuSans-34" transform="translate(202.246094 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(265.869141 0)"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(297.65625 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(361.279297 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(397.363281 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(460.839844 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(499.703125 0)"/>
+ <use xlink:href="#DejaVuSans-76" transform="translate(561.226562 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(620.40625 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(648.189453 0)"/>
+ <use xlink:href="#DejaVuSans-77" transform="translate(709.712891 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(791.5 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(827.583984 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(891.207031 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(954.830078 0)"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(1018.453125 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(1082.076172 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(1118.160156 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(1181.783203 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(1245.40625 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(1281.490234 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(1345.113281 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_2">
+ <g id="line2d_2">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="233.55" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_2">
+ <!-- llama3 -->
+ <g transform="translate(216.592188 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-6c" d="M 603 4863
+L 1178 4863
+L 1178 0
+L 603 0
+L 603 4863
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-61" d="M 2194 1759
+Q 1497 1759 1228 1600
+Q 959 1441 959 1056
+Q 959 750 1161 570
+Q 1363 391 1709 391
+Q 2188 391 2477 730
+Q 2766 1069 2766 1631
+L 2766 1759
+L 2194 1759
+z
+M 3341 1997
+L 3341 0
+L 2766 0
+L 2766 531
+Q 2569 213 2275 61
+Q 1981 -91 1556 -91
+Q 1019 -91 701 211
+Q 384 513 384 1019
+Q 384 1609 779 1909
+Q 1175 2209 1959 2209
+L 2766 2209
+L 2766 2266
+Q 2766 2663 2505 2880
+Q 2244 3097 1772 3097
+Q 1472 3097 1187 3025
+Q 903 2953 641 2809
+L 641 3341
+Q 956 3463 1253 3523
+Q 1550 3584 1831 3584
+Q 2591 3584 2966 3190
+Q 3341 2797 3341 1997
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-6d" d="M 3328 2828
+Q 3544 3216 3844 3400
+Q 4144 3584 4550 3584
+Q 5097 3584 5394 3201
+Q 5691 2819 5691 2113
+L 5691 0
+L 5113 0
+L 5113 2094
+Q 5113 2597 4934 2840
+Q 4756 3084 4391 3084
+Q 3944 3084 3684 2787
+Q 3425 2491 3425 1978
+L 3425 0
+L 2847 0
+L 2847 2094
+Q 2847 2600 2669 2842
+Q 2491 3084 2119 3084
+Q 1678 3084 1418 2786
+Q 1159 2488 1159 1978
+L 1159 0
+L 581 0
+L 581 3500
+L 1159 3500
+L 1159 2956
+Q 1356 3278 1631 3431
+Q 1906 3584 2284 3584
+Q 2666 3584 2933 3390
+Q 3200 3197 3328 2828
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-33" d="M 2597 2516
+Q 3050 2419 3304 2112
+Q 3559 1806 3559 1356
+Q 3559 666 3084 287
+Q 2609 -91 1734 -91
+Q 1441 -91 1130 -33
+Q 819 25 488 141
+L 488 750
+Q 750 597 1062 519
+Q 1375 441 1716 441
+Q 2309 441 2620 675
+Q 2931 909 2931 1356
+Q 2931 1769 2642 2001
+Q 2353 2234 1838 2234
+L 1294 2234
+L 1294 2753
+L 1863 2753
+Q 2328 2753 2575 2939
+Q 2822 3125 2822 3475
+Q 2822 3834 2567 4026
+Q 2313 4219 1838 4219
+Q 1578 4219 1281 4162
+Q 984 4106 628 3988
+L 628 4550
+Q 988 4650 1302 4700
+Q 1616 4750 1894 4750
+Q 2613 4750 3031 4423
+Q 3450 4097 3450 3541
+Q 3450 3153 3228 2886
+Q 3006 2619 2597 2516
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-6c"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(27.783203 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(55.566406 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(116.845703 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(214.257812 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(275.537109 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_3">
+ <g id="line2d_3">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="317.25" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_3">
+ <!-- llama3.3:latest -->
+ <g transform="translate(279.782812 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-3a" d="M 750 794
+L 1409 794
+L 1409 0
+L 750 0
+L 750 794
+z
+M 750 3309
+L 1409 3309
+L 1409 2516
+L 750 2516
+L 750 3309
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-73" d="M 2834 3397
+L 2834 2853
+Q 2591 2978 2328 3040
+Q 2066 3103 1784 3103
+Q 1356 3103 1142 2972
+Q 928 2841 928 2578
+Q 928 2378 1081 2264
+Q 1234 2150 1697 2047
+L 1894 2003
+Q 2506 1872 2764 1633
+Q 3022 1394 3022 966
+Q 3022 478 2636 193
+Q 2250 -91 1575 -91
+Q 1294 -91 989 -36
+Q 684 19 347 128
+L 347 722
+Q 666 556 975 473
+Q 1284 391 1588 391
+Q 1994 391 2212 530
+Q 2431 669 2431 922
+Q 2431 1156 2273 1281
+Q 2116 1406 1581 1522
+L 1381 1569
+Q 847 1681 609 1914
+Q 372 2147 372 2553
+Q 372 3047 722 3315
+Q 1072 3584 1716 3584
+Q 2034 3584 2315 3537
+Q 2597 3491 2834 3397
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-6c"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(27.783203 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(55.566406 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(116.845703 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(214.257812 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(275.537109 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(339.160156 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(370.947266 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(434.570312 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(468.261719 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(496.044922 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(557.324219 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(596.533203 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(658.056641 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(710.15625 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_4">
+ <g id="line2d_4">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="400.95" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_4">
+ <!-- mistral-small -->
+ <g transform="translate(368.496094 399.078438) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-6d"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(97.412109 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(125.195312 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(177.294922 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(216.503906 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(257.617188 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(318.896484 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(346.679688 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(382.763672 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(434.863281 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(532.275391 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(593.554688 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(621.337891 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_5">
+ <g id="line2d_5">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="484.65" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_5">
+ <!-- mixtral:8x7b -->
+ <g transform="translate(452.782031 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-78" d="M 3513 3500
+L 2247 1797
+L 3578 0
+L 2900 0
+L 1881 1375
+L 863 0
+L 184 0
+L 1544 1831
+L 300 3500
+L 978 3500
+L 1906 2253
+L 2834 3500
+L 3513 3500
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-38" d="M 2034 2216
+Q 1584 2216 1326 1975
+Q 1069 1734 1069 1313
+Q 1069 891 1326 650
+Q 1584 409 2034 409
+Q 2484 409 2743 651
+Q 3003 894 3003 1313
+Q 3003 1734 2745 1975
+Q 2488 2216 2034 2216
+z
+M 1403 2484
+Q 997 2584 770 2862
+Q 544 3141 544 3541
+Q 544 4100 942 4425
+Q 1341 4750 2034 4750
+Q 2731 4750 3128 4425
+Q 3525 4100 3525 3541
+Q 3525 3141 3298 2862
+Q 3072 2584 2669 2484
+Q 3125 2378 3379 2068
+Q 3634 1759 3634 1313
+Q 3634 634 3220 271
+Q 2806 -91 2034 -91
+Q 1263 -91 848 271
+Q 434 634 434 1313
+Q 434 1759 690 2068
+Q 947 2378 1403 2484
+z
+M 1172 3481
+Q 1172 3119 1398 2916
+Q 1625 2713 2034 2713
+Q 2441 2713 2670 2916
+Q 2900 3119 2900 3481
+Q 2900 3844 2670 4047
+Q 2441 4250 2034 4250
+Q 1625 4250 1398 4047
+Q 1172 3844 1172 3481
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-62" d="M 3116 1747
+Q 3116 2381 2855 2742
+Q 2594 3103 2138 3103
+Q 1681 3103 1420 2742
+Q 1159 2381 1159 1747
+Q 1159 1113 1420 752
+Q 1681 391 2138 391
+Q 2594 391 2855 752
+Q 3116 1113 3116 1747
+z
+M 1159 2969
+Q 1341 3281 1617 3432
+Q 1894 3584 2278 3584
+Q 2916 3584 3314 3078
+Q 3713 2572 3713 1747
+Q 3713 922 3314 415
+Q 2916 -91 2278 -91
+Q 1894 -91 1617 61
+Q 1341 213 1159 525
+L 1159 0
+L 581 0
+L 581 4863
+L 1159 4863
+L 1159 2969
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-6d"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(97.412109 0)"/>
+ <use xlink:href="#DejaVuSans-78" transform="translate(125.195312 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(184.375 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(223.583984 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(264.697266 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(325.976562 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(353.759766 0)"/>
+ <use xlink:href="#DejaVuSans-38" transform="translate(387.451172 0)"/>
+ <use xlink:href="#DejaVuSans-78" transform="translate(451.074219 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(510.253906 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(573.876953 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_6">
+ <g id="line2d_6">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="568.35" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_6">
+ <!-- deepseek-r1 -->
+ <g transform="translate(537.154688 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-64" d="M 2906 2969
+L 2906 4863
+L 3481 4863
+L 3481 0
+L 2906 0
+L 2906 525
+Q 2725 213 2448 61
+Q 2172 -91 1784 -91
+Q 1150 -91 751 415
+Q 353 922 353 1747
+Q 353 2572 751 3078
+Q 1150 3584 1784 3584
+Q 2172 3584 2448 3432
+Q 2725 3281 2906 2969
+z
+M 947 1747
+Q 947 1113 1208 752
+Q 1469 391 1925 391
+Q 2381 391 2643 752
+Q 2906 1113 2906 1747
+Q 2906 2381 2643 2742
+Q 2381 3103 1925 3103
+Q 1469 3103 1208 2742
+Q 947 2381 947 1747
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-6b" d="M 581 4863
+L 1159 4863
+L 1159 1991
+L 2875 3500
+L 3609 3500
+L 1753 1863
+L 3688 0
+L 2938 0
+L 1159 1709
+L 1159 0
+L 581 0
+L 581 4863
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-31" d="M 794 531
+L 1825 531
+L 1825 4091
+L 703 3866
+L 703 4441
+L 1819 4666
+L 2450 4666
+L 2450 531
+L 3481 531
+L 3481 0
+L 794 0
+L 794 531
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-64"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(125 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(186.523438 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(250 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(302.099609 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(363.623047 0)"/>
+ <use xlink:href="#DejaVuSans-6b" transform="translate(425.146484 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(483.056641 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(519.140625 0)"/>
+ <use xlink:href="#DejaVuSans-31" transform="translate(560.253906 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_7">
+ <g id="line2d_7">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="652.05" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_7">
+ <!-- deepseek-r1:7b -->
+ <g transform="translate(612.814844 399.078438) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-64"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(125 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(186.523438 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(250 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(302.099609 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(363.623047 0)"/>
+ <use xlink:href="#DejaVuSans-6b" transform="translate(425.146484 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(483.056641 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(519.140625 0)"/>
+ <use xlink:href="#DejaVuSans-31" transform="translate(560.253906 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(623.876953 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(657.568359 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(721.191406 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="xtick_8">
+ <g id="line2d_8">
+ <g>
+ <use xlink:href="#m1ed00a0df3" x="735.75" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_8">
+ <!-- qwen3 -->
+ <g transform="translate(719.060156 399.078438) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-71" d="M 947 1747
+Q 947 1113 1208 752
+Q 1469 391 1925 391
+Q 2381 391 2643 752
+Q 2906 1113 2906 1747
+Q 2906 2381 2643 2742
+Q 2381 3103 1925 3103
+Q 1469 3103 1208 2742
+Q 947 2381 947 1747
+z
+M 2906 525
+Q 2725 213 2448 61
+Q 2172 -91 1784 -91
+Q 1150 -91 751 415
+Q 353 922 353 1747
+Q 353 2572 751 3078
+Q 1150 3584 1784 3584
+Q 2172 3584 2448 3432
+Q 2725 3281 2906 2969
+L 2906 3500
+L 3481 3500
+L 3481 -1331
+L 2906 -1331
+L 2906 525
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-6e" d="M 3513 2113
+L 3513 0
+L 2938 0
+L 2938 2094
+Q 2938 2591 2744 2837
+Q 2550 3084 2163 3084
+Q 1697 3084 1428 2787
+Q 1159 2491 1159 1978
+L 1159 0
+L 581 0
+L 581 3500
+L 1159 3500
+L 1159 2956
+Q 1366 3272 1645 3428
+Q 1925 3584 2291 3584
+Q 2894 3584 3203 3211
+Q 3513 2838 3513 2113
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-71"/>
+ <use xlink:href="#DejaVuSans-77" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(145.263672 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(206.787109 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(270.166016 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="text_9">
+ <!-- Model -->
+ <g transform="translate(427.786719 412.756563) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-4d" d="M 628 4666
+L 1569 4666
+L 2759 1491
+L 3956 4666
+L 4897 4666
+L 4897 0
+L 4281 0
+L 4281 4097
+L 3078 897
+L 2444 897
+L 1241 4097
+L 1241 0
+L 628 0
+L 628 4666
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-6f" d="M 1959 3097
+Q 1497 3097 1228 2736
+Q 959 2375 959 1747
+Q 959 1119 1226 758
+Q 1494 397 1959 397
+Q 2419 397 2687 759
+Q 2956 1122 2956 1747
+Q 2956 2369 2687 2733
+Q 2419 3097 1959 3097
+z
+M 1959 3584
+Q 2709 3584 3137 3096
+Q 3566 2609 3566 1747
+Q 3566 888 3137 398
+Q 2709 -91 1959 -91
+Q 1206 -91 779 398
+Q 353 888 353 1747
+Q 353 2609 779 3096
+Q 1206 3584 1959 3584
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-4d"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(86.279297 0)"/>
+ <use xlink:href="#DejaVuSans-64" transform="translate(147.460938 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(210.9375 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(272.460938 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="matplotlib.axis_2">
+ <g id="ytick_1">
+ <g id="line2d_9">
+ <defs>
+ <path id="m7947a91b64" d="M 0 0
+L -3.5 0
+" style="stroke: #000000; stroke-width: 0.8"/>
+ </defs>
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="384.48" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_10">
+ <!-- 0 -->
+ <g transform="translate(94.6375 388.279219) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-30"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_2">
+ <g id="line2d_10">
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="317.952" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_11">
+ <!-- 20 -->
+ <g transform="translate(88.275 321.751219) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-32"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_3">
+ <g id="line2d_11">
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="251.424" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_12">
+ <!-- 40 -->
+ <g transform="translate(88.275 255.223219) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-34"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_4">
+ <g id="line2d_12">
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="184.896" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_13">
+ <!-- 60 -->
+ <g transform="translate(88.275 188.695219) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-36" d="M 2113 2584
+Q 1688 2584 1439 2293
+Q 1191 2003 1191 1497
+Q 1191 994 1439 701
+Q 1688 409 2113 409
+Q 2538 409 2786 701
+Q 3034 994 3034 1497
+Q 3034 2003 2786 2293
+Q 2538 2584 2113 2584
+z
+M 3366 4563
+L 3366 3988
+Q 3128 4100 2886 4159
+Q 2644 4219 2406 4219
+Q 1781 4219 1451 3797
+Q 1122 3375 1075 2522
+Q 1259 2794 1537 2939
+Q 1816 3084 2150 3084
+Q 2853 3084 3261 2657
+Q 3669 2231 3669 1497
+Q 3669 778 3244 343
+Q 2819 -91 2113 -91
+Q 1303 -91 875 529
+Q 447 1150 447 2328
+Q 447 3434 972 4092
+Q 1497 4750 2381 4750
+Q 2619 4750 2861 4703
+Q 3103 4656 3366 4563
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-36"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_5">
+ <g id="line2d_13">
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="118.368" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_14">
+ <!-- 80 -->
+ <g transform="translate(88.275 122.167219) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-38"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="ytick_6">
+ <g id="line2d_14">
+ <g>
+ <use xlink:href="#m7947a91b64" x="108" y="51.84" style="stroke: #000000; stroke-width: 0.8"/>
+ </g>
+ </g>
+ <g id="text_15">
+ <!-- 100 -->
+ <g transform="translate(81.9125 55.639219) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-31"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(127.246094 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="text_16">
+ <!-- Share of money assigned to oneself -->
+ <g transform="translate(75.832812 307.896719) rotate(-90) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-53" d="M 3425 4513
+L 3425 3897
+Q 3066 4069 2747 4153
+Q 2428 4238 2131 4238
+Q 1616 4238 1336 4038
+Q 1056 3838 1056 3469
+Q 1056 3159 1242 3001
+Q 1428 2844 1947 2747
+L 2328 2669
+Q 3034 2534 3370 2195
+Q 3706 1856 3706 1288
+Q 3706 609 3251 259
+Q 2797 -91 1919 -91
+Q 1588 -91 1214 -16
+Q 841 59 441 206
+L 441 856
+Q 825 641 1194 531
+Q 1563 422 1919 422
+Q 2459 422 2753 634
+Q 3047 847 3047 1241
+Q 3047 1584 2836 1778
+Q 2625 1972 2144 2069
+L 1759 2144
+Q 1053 2284 737 2584
+Q 422 2884 422 3419
+Q 422 4038 858 4394
+Q 1294 4750 2059 4750
+Q 2388 4750 2728 4690
+Q 3069 4631 3425 4513
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-68" d="M 3513 2113
+L 3513 0
+L 2938 0
+L 2938 2094
+Q 2938 2591 2744 2837
+Q 2550 3084 2163 3084
+Q 1697 3084 1428 2787
+Q 1159 2491 1159 1978
+L 1159 0
+L 581 0
+L 581 4863
+L 1159 4863
+L 1159 2956
+Q 1366 3272 1645 3428
+Q 1925 3584 2291 3584
+Q 2894 3584 3203 3211
+Q 3513 2838 3513 2113
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-20" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-66" d="M 2375 4863
+L 2375 4384
+L 1825 4384
+Q 1516 4384 1395 4259
+Q 1275 4134 1275 3809
+L 1275 3500
+L 2222 3500
+L 2222 3053
+L 1275 3053
+L 1275 0
+L 697 0
+L 697 3053
+L 147 3053
+L 147 3500
+L 697 3500
+L 697 3744
+Q 697 4328 969 4595
+Q 1241 4863 1831 4863
+L 2375 4863
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-79" d="M 2059 -325
+Q 1816 -950 1584 -1140
+Q 1353 -1331 966 -1331
+L 506 -1331
+L 506 -850
+L 844 -850
+Q 1081 -850 1212 -737
+Q 1344 -625 1503 -206
+L 1606 56
+L 191 3500
+L 800 3500
+L 1894 763
+L 2988 3500
+L 3597 3500
+L 2059 -325
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-53"/>
+ <use xlink:href="#DejaVuSans-68" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(126.855469 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(188.134766 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(226.998047 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(288.521484 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(320.308594 0)"/>
+ <use xlink:href="#DejaVuSans-66" transform="translate(381.490234 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(416.695312 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(448.482422 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(545.894531 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(607.076172 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(670.455078 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(731.978516 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(791.158203 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(822.945312 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(884.224609 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(936.324219 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(988.423828 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(1016.207031 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(1079.683594 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1143.0625 0)"/>
+ <use xlink:href="#DejaVuSans-64" transform="translate(1204.585938 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1268.0625 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(1299.849609 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(1339.058594 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1400.240234 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(1432.027344 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(1493.208984 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1556.587891 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(1618.111328 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1670.210938 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(1731.734375 0)"/>
+ <use xlink:href="#DejaVuSans-66" transform="translate(1759.517578 0)"/>
+ </g>
+ </g>
+ </g>
+ <g id="line2d_15">
+ <path d="M 143.028324 209.844
+L 156.671676 209.844
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_16">
+ <path d="M 116.37977 184.896
+L 183.32023 184.896
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_17">
+ <path d="M 116.37977 184.896
+L 183.32023 184.896
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_18">
+ <path d="M 218.439565 209.844
+L 248.660435 209.844
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_19">
+ <path d="M 200.108297 53.5032
+L 266.991703 53.5032
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_20">
+ <path d="M 200.224108 51.84
+L 266.875892 51.84
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_21">
+ <path d="M 283.77 184.896
+L 350.73 184.896
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke: #1f1f1f; stroke-width: 1.25; stroke-linecap: square"/>
+ </g>
+ <g id="line2d_22">
+ <path d="M 367.627001 218.16
+L 434.272999 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_23">
+ <path d="M 367.470918 214.8336
+L 434.429082 214.8336
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_24">
+ <path d="M 393.094353 151.632
+L 408.805647 151.632
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_25">
+ <path d="M 451.17 218.16
+L 518.13 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_26">
+ <path d="M 451.17 218.16
+L 518.13 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_27">
+ <path d="M 451.17 218.16
+L 518.13 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_28">
+ <path d="M 534.919869 384.48
+L 601.780131 384.48
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_29">
+ <path d="M 534.919869 384.48
+L 601.780131 384.48
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_30">
+ <path d="M 534.919869 384.48
+L 601.780131 384.48
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_31">
+ <path d="M 618.618479 218.16
+L 685.481521 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_32">
+ <path d="M 618.618479 218.16
+L 685.481521 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_33">
+ <path d="M 638.446218 93.42
+L 665.653782 93.42
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_34">
+ <path d="M 705.37047 85.104
+L 766.12953 85.104
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_35">
+ <path d="M 702.35754 68.472
+L 769.14246 68.472
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 3.125,1.25; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_36">
+ <path d="M 703.4836 55.1664
+L 768.0164 55.1664
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 1.5625,0.9375; stroke-dashoffset: 0; stroke: #1f1f1f; stroke-width: 1.25"/>
+ </g>
+ <g id="line2d_37">
+ <path d="M 108 151.632
+L 777.6 151.632
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #7abaff; stroke-width: 2"/>
+ </g>
+ <g id="line2d_38">
+ <path d="M 108 218.16
+L 777.6 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #32a68c; stroke-width: 2"/>
+ </g>
+ <g id="line2d_39">
+ <path d="M 108 184.896
+L 777.6 184.896
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #4b9f7d; stroke-width: 2"/>
+ </g>
+ <g id="line2d_40">
+ <path d="M 108 218.16
+L 777.6 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #ff6941; stroke-width: 2"/>
+ </g>
+ <g id="line2d_41">
+ <path d="M 108 251.424
+L 777.6 251.424
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #f1a61a; stroke-width: 2"/>
+ </g>
+ <g id="line2d_42">
+ <path d="M 108 184.896
+L 777.6 184.896
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #9a7bff; stroke-width: 2"/>
+ </g>
+ <g id="line2d_43">
+ <path d="M 108 218.16
+L 777.6 218.16
+" clip-path="url(#p229f3ceefe)" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #c02942; stroke-width: 2"/>
+ </g>
+ <g id="patch_3">
+ <path d="M 108 384.48
+L 108 51.84
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+ </g>
+ <g id="patch_4">
+ <path d="M 777.6 384.48
+L 777.6 51.84
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+ </g>
+ <g id="patch_5">
+ <path d="M 108 384.48
+L 777.6 384.48
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+ </g>
+ <g id="patch_6">
+ <path d="M 108 51.84
+L 777.6 51.84
+" style="fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
+ </g>
+ <g id="text_17">
+ <!-- 60.0 -->
+ <g transform="translate(138.717187 182.816312) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-36"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_18">
+ <!-- 99.5 -->
+ <g transform="translate(222.417188 51.423513) scale(0.1 -0.1)">
+ <defs>
+ <path id="DejaVuSans-39" d="M 703 97
+L 703 672
+Q 941 559 1184 500
+Q 1428 441 1663 441
+Q 2288 441 2617 861
+Q 2947 1281 2994 2138
+Q 2813 1869 2534 1725
+Q 2256 1581 1919 1581
+Q 1219 1581 811 2004
+Q 403 2428 403 3163
+Q 403 3881 828 4315
+Q 1253 4750 1959 4750
+Q 2769 4750 3195 4129
+Q 3622 3509 3622 2328
+Q 3622 1225 3098 567
+Q 2575 -91 1691 -91
+Q 1453 -91 1209 -44
+Q 966 3 703 97
+z
+M 1959 2075
+Q 2384 2075 2632 2365
+Q 2881 2656 2881 3163
+Q 2881 3666 2632 3958
+Q 2384 4250 1959 4250
+Q 1534 4250 1286 3958
+Q 1038 3666 1038 3163
+Q 1038 2656 1286 2365
+Q 1534 2075 1959 2075
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-39"/>
+ <use xlink:href="#DejaVuSans-39" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_19">
+ <!-- 60.0 -->
+ <g transform="translate(306.117188 182.816312) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-36"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_20">
+ <!-- 51.0 -->
+ <g transform="translate(389.817188 212.753912) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-35"/>
+ <use xlink:href="#DejaVuSans-31" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_21">
+ <!-- 50.0 -->
+ <g transform="translate(473.517187 216.080312) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-35"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_22">
+ <!-- 0.0 -->
+ <g transform="translate(560.398438 382.400312) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-30"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(95.410156 0)"/>
+ </g>
+ </g>
+ <g id="text_23">
+ <!-- 50.0 -->
+ <g transform="translate(640.917188 216.080312) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-35"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_24">
+ <!-- 95.0 -->
+ <g transform="translate(724.617188 66.392313) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-39"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(63.623047 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(127.246094 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(159.033203 0)"/>
+ </g>
+ </g>
+ <g id="text_25">
+ <!-- Distribution of personal share by model in the ultimatum game -->
+ <g transform="translate(252.9225 45.84) scale(0.12 -0.12)">
+ <defs>
+ <path id="DejaVuSans-44" d="M 1259 4147
+L 1259 519
+L 2022 519
+Q 2988 519 3436 956
+Q 3884 1394 3884 2338
+Q 3884 3275 3436 3711
+Q 2988 4147 2022 4147
+L 1259 4147
+z
+M 628 4666
+L 1925 4666
+Q 3281 4666 3915 4102
+Q 4550 3538 4550 2338
+Q 4550 1131 3912 565
+Q 3275 0 1925 0
+L 628 0
+L 628 4666
+z
+" transform="scale(0.015625)"/>
+ <path id="DejaVuSans-75" d="M 544 1381
+L 544 3500
+L 1119 3500
+L 1119 1403
+Q 1119 906 1312 657
+Q 1506 409 1894 409
+Q 2359 409 2629 706
+Q 2900 1003 2900 1516
+L 2900 3500
+L 3475 3500
+L 3475 0
+L 2900 0
+L 2900 538
+Q 2691 219 2414 64
+Q 2138 -91 1772 -91
+Q 1169 -91 856 284
+Q 544 659 544 1381
+z
+M 1991 3584
+L 1991 3584
+z
+" transform="scale(0.015625)"/>
+ </defs>
+ <use xlink:href="#DejaVuSans-44"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(77.001953 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(104.785156 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(156.884766 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(196.09375 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(237.207031 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(264.990234 0)"/>
+ <use xlink:href="#DejaVuSans-75" transform="translate(328.466797 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(391.845703 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(431.054688 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(458.837891 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(520.019531 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(583.398438 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(615.185547 0)"/>
+ <use xlink:href="#DejaVuSans-66" transform="translate(676.367188 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(711.572266 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(743.359375 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(806.835938 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(868.359375 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(909.472656 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(961.572266 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(1022.753906 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(1086.132812 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(1147.412109 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1175.195312 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(1206.982422 0)"/>
+ <use xlink:href="#DejaVuSans-68" transform="translate(1259.082031 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(1322.460938 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(1383.740234 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1422.603516 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1484.126953 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(1515.914062 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1579.390625 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1638.570312 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(1670.357422 0)"/>
+ <use xlink:href="#DejaVuSans-6f" transform="translate(1767.769531 0)"/>
+ <use xlink:href="#DejaVuSans-64" transform="translate(1828.951172 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1892.427734 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(1953.951172 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1981.734375 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(2013.521484 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(2041.304688 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(2104.683594 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(2136.470703 0)"/>
+ <use xlink:href="#DejaVuSans-68" transform="translate(2175.679688 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(2239.058594 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(2300.582031 0)"/>
+ <use xlink:href="#DejaVuSans-75" transform="translate(2332.369141 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(2395.748047 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(2423.53125 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(2462.740234 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(2490.523438 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(2587.935547 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(2649.214844 0)"/>
+ <use xlink:href="#DejaVuSans-75" transform="translate(2688.423828 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(2751.802734 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(2849.214844 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(2881.001953 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(2944.478516 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(3005.757812 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(3103.169922 0)"/>
+ </g>
+ </g>
+ <g id="legend_1">
+ <g id="patch_7">
+ <path d="M 333.91875 379.48
+L 551.68125 379.48
+Q 553.68125 379.48 553.68125 377.48
+L 553.68125 275.733125
+Q 553.68125 273.733125 551.68125 273.733125
+L 333.91875 273.733125
+Q 331.91875 273.733125 331.91875 275.733125
+L 331.91875 377.48
+Q 331.91875 379.48 333.91875 379.48
+z
+" style="fill: #ffffff; opacity: 0.8; stroke: #cccccc; stroke-linejoin: miter"/>
+ </g>
+ <g id="line2d_44">
+ <path d="M 335.91875 281.831563
+L 345.91875 281.831563
+L 355.91875 281.831563
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #7abaff; stroke-width: 2"/>
+ </g>
+ <g id="text_26">
+ <!-- gpt-4.5-preview-2025-02-27 strategy -->
+ <g transform="translate(363.91875 285.331563) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-67"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(126.953125 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(166.162109 0)"/>
+ <use xlink:href="#DejaVuSans-34" transform="translate(202.246094 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(265.869141 0)"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(297.65625 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(361.279297 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(397.363281 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(460.839844 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(499.703125 0)"/>
+ <use xlink:href="#DejaVuSans-76" transform="translate(561.226562 0)"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(620.40625 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(648.189453 0)"/>
+ <use xlink:href="#DejaVuSans-77" transform="translate(709.712891 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(791.5 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(827.583984 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(891.207031 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(954.830078 0)"/>
+ <use xlink:href="#DejaVuSans-35" transform="translate(1018.453125 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(1082.076172 0)"/>
+ <use xlink:href="#DejaVuSans-30" transform="translate(1118.160156 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(1181.783203 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(1245.40625 0)"/>
+ <use xlink:href="#DejaVuSans-32" transform="translate(1281.490234 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(1345.113281 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(1408.736328 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(1440.523438 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(1492.623047 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(1531.832031 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(1572.945312 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(1634.224609 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1673.433594 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(1734.957031 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1798.433594 0)"/>
+ </g>
+ </g>
+ <g id="line2d_45">
+ <path d="M 335.91875 296.509688
+L 345.91875 296.509688
+L 355.91875 296.509688
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #32a68c; stroke-width: 2"/>
+ </g>
+ <g id="text_27">
+ <!-- llama3 strategy -->
+ <g transform="translate(363.91875 300.009688) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-6c"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(27.783203 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(55.566406 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(116.845703 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(214.257812 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(275.537109 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(339.160156 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(370.947266 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(423.046875 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(462.255859 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(503.369141 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(564.648438 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(603.857422 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(665.380859 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(728.857422 0)"/>
+ </g>
+ </g>
+ <g id="line2d_46">
+ <path d="M 335.91875 311.187813
+L 345.91875 311.187813
+L 355.91875 311.187813
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #4b9f7d; stroke-width: 2"/>
+ </g>
+ <g id="text_28">
+ <!-- llama3.3:latest strategy -->
+ <g transform="translate(363.91875 314.687813) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-6c"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(27.783203 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(55.566406 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(116.845703 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(214.257812 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(275.537109 0)"/>
+ <use xlink:href="#DejaVuSans-2e" transform="translate(339.160156 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(370.947266 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(434.570312 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(468.261719 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(496.044922 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(557.324219 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(596.533203 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(658.056641 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(710.15625 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(749.365234 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(781.152344 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(833.251953 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(872.460938 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(913.574219 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(974.853516 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1014.0625 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(1075.585938 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1139.0625 0)"/>
+ </g>
+ </g>
+ <g id="line2d_47">
+ <path d="M 335.91875 325.865938
+L 345.91875 325.865938
+L 355.91875 325.865938
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #ff6941; stroke-width: 2"/>
+ </g>
+ <g id="text_29">
+ <!-- mistral-small strategy -->
+ <g transform="translate(363.91875 329.365938) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-6d"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(97.412109 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(125.195312 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(177.294922 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(216.503906 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(257.617188 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(318.896484 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(346.679688 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(382.763672 0)"/>
+ <use xlink:href="#DejaVuSans-6d" transform="translate(434.863281 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(532.275391 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(593.554688 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(621.337891 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(649.121094 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(680.908203 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(733.007812 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(772.216797 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(813.330078 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(874.609375 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(913.818359 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(975.341797 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1038.818359 0)"/>
+ </g>
+ </g>
+ <g id="line2d_48">
+ <path d="M 335.91875 340.544062
+L 345.91875 340.544062
+L 355.91875 340.544062
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #f1a61a; stroke-width: 2"/>
+ </g>
+ <g id="text_30">
+ <!-- mixtral:8x7b strategy -->
+ <g transform="translate(363.91875 344.044062) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-6d"/>
+ <use xlink:href="#DejaVuSans-69" transform="translate(97.412109 0)"/>
+ <use xlink:href="#DejaVuSans-78" transform="translate(125.195312 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(184.375 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(223.583984 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(264.697266 0)"/>
+ <use xlink:href="#DejaVuSans-6c" transform="translate(325.976562 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(353.759766 0)"/>
+ <use xlink:href="#DejaVuSans-38" transform="translate(387.451172 0)"/>
+ <use xlink:href="#DejaVuSans-78" transform="translate(451.074219 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(510.253906 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(573.876953 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(637.353516 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(669.140625 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(721.240234 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(760.449219 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(801.5625 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(862.841797 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(902.050781 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(963.574219 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1027.050781 0)"/>
+ </g>
+ </g>
+ <g id="line2d_49">
+ <path d="M 335.91875 355.222188
+L 345.91875 355.222188
+L 355.91875 355.222188
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #9a7bff; stroke-width: 2"/>
+ </g>
+ <g id="text_31">
+ <!-- deepseek-r1:7b strategy -->
+ <g transform="translate(363.91875 358.722188) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-64"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(125 0)"/>
+ <use xlink:href="#DejaVuSans-70" transform="translate(186.523438 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(250 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(302.099609 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(363.623047 0)"/>
+ <use xlink:href="#DejaVuSans-6b" transform="translate(425.146484 0)"/>
+ <use xlink:href="#DejaVuSans-2d" transform="translate(483.056641 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(519.140625 0)"/>
+ <use xlink:href="#DejaVuSans-31" transform="translate(560.253906 0)"/>
+ <use xlink:href="#DejaVuSans-3a" transform="translate(623.876953 0)"/>
+ <use xlink:href="#DejaVuSans-37" transform="translate(657.568359 0)"/>
+ <use xlink:href="#DejaVuSans-62" transform="translate(721.191406 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(784.667969 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(816.455078 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(868.554688 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(907.763672 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(948.876953 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(1010.15625 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(1049.365234 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(1110.888672 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(1174.365234 0)"/>
+ </g>
+ </g>
+ <g id="line2d_50">
+ <path d="M 335.91875 369.900313
+L 345.91875 369.900313
+L 355.91875 369.900313
+" style="fill: none; stroke-dasharray: 7.4,3.2; stroke-dashoffset: 0; stroke: #c02942; stroke-width: 2"/>
+ </g>
+ <g id="text_32">
+ <!-- qwen3 strategy -->
+ <g transform="translate(363.91875 373.400313) scale(0.1 -0.1)">
+ <use xlink:href="#DejaVuSans-71"/>
+ <use xlink:href="#DejaVuSans-77" transform="translate(63.476562 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(145.263672 0)"/>
+ <use xlink:href="#DejaVuSans-6e" transform="translate(206.787109 0)"/>
+ <use xlink:href="#DejaVuSans-33" transform="translate(270.166016 0)"/>
+ <use xlink:href="#DejaVuSans-20" transform="translate(333.789062 0)"/>
+ <use xlink:href="#DejaVuSans-73" transform="translate(365.576172 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(417.675781 0)"/>
+ <use xlink:href="#DejaVuSans-72" transform="translate(456.884766 0)"/>
+ <use xlink:href="#DejaVuSans-61" transform="translate(497.998047 0)"/>
+ <use xlink:href="#DejaVuSans-74" transform="translate(559.277344 0)"/>
+ <use xlink:href="#DejaVuSans-65" transform="translate(598.486328 0)"/>
+ <use xlink:href="#DejaVuSans-67" transform="translate(660.009766 0)"/>
+ <use xlink:href="#DejaVuSans-79" transform="translate(723.486328 0)"/>
+ </g>
+ </g>
+ </g>
+ </g>
+ </g>
+ <defs>
+ <clipPath id="p229f3ceefe">
+ <rect x="108" y="51.84" width="669.6" height="332.64"/>
+ </clipPath>
+ </defs>
+</svg>
diff --git a/requirements.txt b/requirements.txt
index 09a0f9b..052fdb3 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -17,11 +17,11 @@ keyring==25.6.0
lockfile==0.12.2
matplotlib==3.10.1
mock==5.1.0
-numpy==2.2.3
+numpy~=2.2.4
pandas==2.2.3
Pillow==11.1.0
-protobuf==5.29.3
-pydantic==2.10.6
+protobuf~=5.29.4
+pydantic~=2.11.1
pyOpenSSL==25.0.0
railroad==0.5.0
scipy==1.15.2
@@ -32,3 +32,8 @@ tornado==6.4.2
truststore==0.10.1
urllib3_secure_extra==0.1.0
xmlrpclib==1.0.1
+
+requests~=2.32.3
+httpx~=0.28.1
+pip~=25.0.1
+distro~=1.9.0
\ No newline at end of file
diff --git a/src/dictator/dictator.py b/src/dictator/dictator.py
index 6b06abd..f62875e 100644
--- a/src/dictator/dictator.py
+++ b/src/dictator/dictator.py
@@ -1,7 +1,7 @@
+# Maxime MORGE <maxime.morge@univ-lyon1.fr>
import os
import asyncio
import json
-import logging
import requests
from typing import Dict
from pydantic import BaseModel
diff --git a/src/dictator/dictator_experiments.py b/src/dictator/dictator_experiments.py
index a74b429..bfc7bf7 100644
--- a/src/dictator/dictator_experiments.py
+++ b/src/dictator/dictator_experiments.py
@@ -1,6 +1,4 @@
import asyncio
-import statistics
-import pandas as pd
from dictator import Dictator
class DictatorExperiment:
diff --git a/src/ultimatum/__init__.py b/src/ultimatum/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/ultimatum/proposer.py b/src/ultimatum/proposer.py
new file mode 100644
index 0000000..a65202f
--- /dev/null
+++ b/src/ultimatum/proposer.py
@@ -0,0 +1,284 @@
+import os
+import asyncio
+import json
+import requests
+from typing import Dict
+from pydantic import BaseModel
+from autogen_agentchat.agents import AssistantAgent
+from autogen_agentchat.messages import TextMessage
+from autogen_core import CancellationToken
+from autogen_ext.models.openai import OpenAIChatCompletionClient
+import re
+
+# Load API keys from environment variables
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+if not OPENAI_API_KEY:
+ raise ValueError("Missing OPENAI_API_KEY. Set it as an environment variable.")
+PAGODA_API_KEY = os.getenv("PAGODA_API_KEY")
+if not PAGODA_API_KEY:
+ raise ValueError("Missing PAGODA_API_KEY. Set it as an environment variable.")
+
+# Define the expected response format as a Pydantic model
+class AgentResponse(BaseModel):
+ my_share: int
+ other_share: int
+ reasoning: str
+
+# The ultimatum game simulation class
+class Proposer:
+ def __init__(self, amount: int, model: str, temperature: float, strategy=False, max_retries: int = 3):
+ self.debug = False
+ self.amount = amount
+ self.model = model
+ self.temperature = temperature
+ self.strategy = strategy
+ self.max_retries = max_retries
+
+ is_openai_model = model.startswith("gpt")
+ is_pagoda_model = ":" in model
+
+ base_url = (
+ "https://api.openai.com/v1" if is_openai_model else
+ "https://ollama-ui.pagoda.liris.cnrs.fr/ollama/api/generate" if is_pagoda_model else
+ "http://localhost:11434/v1"
+ )
+ self.base_url = base_url
+
+ if self.debug:
+ print(f"Using model: {model}")
+ print(f"Using base URL: {base_url}")
+
+ key = OPENAI_API_KEY if is_openai_model else PAGODA_API_KEY
+
+ model_info = {
+ "temperature": self.temperature,
+ "function_calling": True,
+ "parallel_tool_calls": False,
+ "family": "unknown",
+ "json_output": True,
+ "vision": False
+ }
+
+ self.model_client = OpenAIChatCompletionClient(
+ model=self.model,
+ base_url=base_url,
+ api_key=key,
+ model_info=model_info,
+ response_format=AgentResponse
+ )
+
+
+ async def run(self) -> Dict:
+ """Runs the model if strategy is False, otherwise uses a classical method."""
+ if self.strategy:
+ return self.apply_strategy()
+
+ instruction = f"""
+ You participate in an economics experiment. In this experiment each of you will
+ be paired with a different person. You will not be told who these people are
+ either during or after the experiment, and they will not be told who you are
+ either during or after the experiment.
+
+ The experiment is conducted as follows: A sum of ${self.amount} has been provisionally
+ allocated to each pair and the person A can propose how much of this each person
+ is to receive. A proposal form will then be sent to the person B.
+
+ The person B will then be given a chance to accept or reject the proposal. If
+ the person B accepts the proposal, then the amount of money will be divided as
+ specified in the proposal. If the person B rejects the proposal, then both
+ people in the pair receive zero. A response form will be sent to the person A.
+
+ You are person A.
+
+ Return the response in JSON format with `my_share`, `other_share`, and `reasoning`.
+ """
+ if self.debug:
+ print(instruction)
+
+ is_pagoda_model = ":" in self.model
+ if is_pagoda_model:
+ return await self.run_pagoda(instruction)
+
+ for attempt in range(self.max_retries):
+ agent = AssistantAgent(
+ name="Proposer",
+ model_client=self.model_client,
+ system_message="You are a helpful assistant."
+ )
+
+ response = await agent.on_messages(
+ [TextMessage(content=instruction, source="user")],
+ cancellation_token=CancellationToken(),
+ )
+
+ try:
+ # Correct: get the content from the chat message
+ raw_text = response.chat_message.content
+
+ # Debug: show the raw content
+ print(f"Raw content (Attempt {attempt + 1}): {raw_text}")
+
+ # Try to load JSON directly
+ try:
+ response_json = json.loads(raw_text)
+ except json.JSONDecodeError:
+ # If it's wrapped in ```json ... ```, extract it
+ match = re.search(r'```json\s*(.*?)\s*```', raw_text, re.DOTALL)
+ if match:
+ response_json = json.loads(match.group(1))
+ else:
+ print(f"Could not parse JSON from response (Attempt {attempt + 1})")
+ continue
+
+ agent_response = AgentResponse(**response_json)
+ my_share, other_share = agent_response.my_share, agent_response.other_share
+
+ # Validate shares
+ if 0 <= my_share <= self.amount and 0 <= other_share <= self.amount and my_share + other_share <= self.amount:
+ return agent_response
+ else:
+ print(f"Invalid values in response (Attempt {attempt + 1}): {response_json}")
+
+ except Exception as e:
+ print(f"Error in OpenAI response handling (Attempt {attempt + 1}): {e}")
+
+ raise ValueError("Model failed to provide a valid response after multiple attempts.")
+
+ async def run_pagoda(self, instruction) -> Dict:
+ """Runs the Pagoda model using a direct request."""
+ url = self.base_url
+
+ headers = {
+ "Authorization": f"Bearer {PAGODA_API_KEY}",
+ "Content-Type": "application/json"
+ }
+
+ payload = {
+ "model": self.model,
+ "temperature": self.temperature,
+ "prompt": instruction,
+ "stream": False,
+ "response_format": {
+ "type": "json_schema",
+ "json_schema": {
+ "name": "AgentResponse",
+ "strict": True,
+ "schema": {
+ "title": "AgentResponse",
+ "type": "object",
+ "properties": {
+ "my_share": {
+ "title": "My Share",
+ "type": "integer"
+ },
+ "other_share": {
+ "title": "Other Share",
+ "type": "integer"
+ },
+ "reasoning": {
+ "title": "Reasoning",
+ "type": "string"
+ }
+ },
+ "required": ["my_share", "other_share", "reasoning"],
+ "additionalProperties": False
+ }
+ }
+ }
+ }
+
+ for attempt in range(self.max_retries):
+ try:
+ response = requests.post(url, headers=headers, json=payload)
+ response.raise_for_status()
+
+ # Get the JSON response
+ response_data = response.json()
+
+ # Debug: print the raw response to check if fields are missing or named differently
+ if self.debug:
+ print(f"Raw response (Attempt {attempt+1}): {response_data}")
+
+ # The response field should be parsed correctly if it's already valid JSON
+ response_json = response_data.get('response', '')
+
+ # If the response is a string containing JSON, we need to extract and parse it
+ if isinstance(response_json, str):
+ # Try to parse the response as JSON
+ try:
+ response_dict = json.loads(response_json)
+ except json.JSONDecodeError:
+ # If the response is not valid JSON, apply regex to extract the JSON portion
+ match = re.search(r"```json(.*?)```", response_json, re.DOTALL)
+ if match:
+ response_dict = json.loads(match.group(1))
+ else:
+ print(f"Invalid response format detected (Attempt {attempt + 1}): {response_json}")
+ continue
+ elif isinstance(response_json, dict):
+ # If response_json is already a dictionary, just use it
+ response_dict = response_json
+ else:
+ print(f"Unexpected format in 'response' field (Attempt {attempt + 1}): {response_json}")
+ continue
+
+ # Validate the response structure
+ agent_response = AgentResponse(**response_dict)
+ my_share, other_share = agent_response.my_share, agent_response.other_share
+
+ # Validate that the values are within expected bounds
+ if 0 <= my_share <= self.amount and 0 <= other_share <= self.amount and my_share + other_share <= self.amount:
+ return agent_response.dict()
+ else:
+ print(f"Invalid response detected (Attempt {attempt + 1}): {response_dict}")
+
+ except Exception as e:
+ print(f"Error in Pagoda request (Attempt {attempt + 1}): {e}")
+
+ raise ValueError("Pagoda model failed to provide a valid response after multiple attempts.")
+
+ def apply_strategy(self) -> Dict:
+ """Generates a response based on predefined strategies."""
+ if self.model == "gpt-4.5-preview-2025-02-27":
+ my_share = int(self.amount * 0.7)
+ other_share = self.amount - my_share
+ reasoning = (
+ f"I offered ${my_share} to myself and ${other_share} to the other player. "
+ "This 70-30 split is slightly in my favor but still leaves a meaningful amount "
+ "for the other player, increasing the chance of acceptance while maximizing my gain."
+ )
+ return {"my_share": my_share, "other_share": other_share, "reasoning": reasoning}
+ if self.model in ["mixtral:8x7b"]:
+ if self.amount <= 10:
+ my_share= round(self.amount * 0.7),
+ other_share= round(self.amount * 0.3),
+ reasoning= f'Since the amount ({self.amount}) is small, I will take a larger share of {round(self.amount * 0.7)} and give the other party a smaller share of {round(self.amount * 0.3)}.',
+ else:
+ my_share= round(self.amount * 0.4),
+ other_share= round(self.amount * 0.6),
+ reasoning= f'Since the amount ({self.amount}) is large, I will take a smaller share of {round(self.amount * 0.4)} and give the other party a larger share of {round(self.amount * 0.6)}.',
+ agent_response = AgentResponse(my_share=my_share, other_share=other_share, reasoning=reasoning)
+ return agent_response.dict()
+ if self.model in ["llama3.3:latest", "deepseek-r1:7b"]:
+ my_share = int(0.6 * self.amount)
+ other_share = self.amount - my_share
+ reasoning = "I chose this split because it seems like a fair and reasonable division."
+ agent_response = AgentResponse(my_share=my_share, other_share=other_share, reasoning=reasoning)
+ return agent_response.dict()
+ if self.model in ["mistral_small","qwen3", "llama3"]:
+ half_amount = self.amount // 2
+ return {
+ "my_share": half_amount,
+ "other_share": half_amount,
+ "reasoning": "Split equally between both players."
+ }
+ if self.model in ["deepseek-r1"]:
+ return None
+ return None
+ return None
+
+ # Run the async function and return the response
+if __name__ == "__main__":
+ agent = Proposer(amount=100, model="llama3", temperature=0.7, strategy=False) # "llama3.3:latest", "mixtral:8x7b"
+ response_json = asyncio.run(agent.run())
+ print(response_json)
\ No newline at end of file
diff --git a/src/ultimatum/proposer_draw_violin.py b/src/ultimatum/proposer_draw_violin.py
new file mode 100644
index 0000000..9a6efca
--- /dev/null
+++ b/src/ultimatum/proposer_draw_violin.py
@@ -0,0 +1,73 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Definition of the color palette
+color_palette = {
+ 'random': '#333333', # Black
+ 'gpt-4.5-preview-2025-02-27': '#7abaff', # BlueEscape
+ 'llama3': '#32a68c', # GreenFuture
+ 'llama3.3:latest': '#4b9f7d', # GreenLlama3.3
+ 'mistral-small': '#ff6941', # WarmOrange
+ 'mixtral:8x7b': '#f1a61a', # YellowMixtral
+ 'deepseek-r1': '#5862ed', # InclusiveIndigo
+ 'deepseek-r1:7b': '#9a7bff', # PurpleDeepseek-r1:7b
+ 'qwen3': '#c02942'
+}
+
+# Load the data
+data = pd.read_csv("../../data/ultimatum/proposer.csv") # Replace with the correct path to your CSV file
+
+# Specify the order of models for the x-axis
+model_order = [
+ 'gpt-4.5-preview-2025-02-27',
+ 'llama3', 'llama3.3:latest', # Place llama3 and llama3.3:latest together
+ 'mistral-small', 'mixtral:8x7b', # Bring mistral-small and mixtral:8x7b closer
+ 'deepseek-r1', 'deepseek-r1:7b',
+ 'qwen3'
+]
+
+# Create the violin plot
+plt.figure(figsize=(12, 6))
+sns.violinplot(
+ data=data,
+ x="model",
+ y="my_share",
+ hue="model", # Use hue to manage the colors
+ palette=color_palette,
+ inner="quartile", # Displays quartiles inside the violin
+ density_norm="width", # Normalizes the width of the violins for comparison
+ order=model_order # Explicitly set the order of the models on the x-axis
+)
+
+# Add vertical lines for strategies
+strategy_values = {
+ 'gpt-4.5-preview-2025-02-27': 70,
+ 'llama3': 50,
+ 'llama3.3:latest': 60,
+ 'mistral-small': 50,
+ 'mixtral:8x7b': 40,
+ 'deepseek-r1:7b': 60,
+ 'qwen3': 50
+}
+
+for model, value in strategy_values.items():
+ plt.axhline(y=value, color=color_palette[model], linestyle="dashed", linewidth=2, label=f"{model} strategy")
+
+# Ajouter les valeurs médianes comme annotations sur le graphique
+for model in model_order:
+ mediane = data[data['model'] == model]['my_share'].median()
+ plt.text(model_order.index(model), mediane, f'{mediane:.1f}',
+ horizontalalignment='center', verticalalignment='bottom')
+
+# Set the y-axis limits between 0 and 100
+plt.ylim(0, 100)
+
+# Labels and title
+plt.xlabel("Model")
+plt.ylabel("Share of money assigned to oneself")
+plt.title("Distribution of personal share by model in the ultimatum game")
+plt.legend()
+
+# Save and display the plot
+plt.savefig("../../figures/ultimatum/proposer_violin.svg", format="svg")
\ No newline at end of file
diff --git a/src/ultimatum/proposer_experiments.py b/src/ultimatum/proposer_experiments.py
new file mode 100644
index 0000000..e12c42b
--- /dev/null
+++ b/src/ultimatum/proposer_experiments.py
@@ -0,0 +1,49 @@
+
+import asyncio
+from proposer import Proposer
+
+class UltimatumExperiment:
+ debug = True
+
+ def __init__(self, models: list[str], temperature: float, amount: int, iterations: int, output_file: str):
+ self.models = models
+ self.temperature = temperature
+ self.amount = amount
+ self.iterations = iterations
+ self.output_file = output_file
+
+ with open(self.output_file, 'w', encoding='utf-8') as f:
+ f.write("iteration,model,temperature,amount,my_share,other_share,reasoning\n")
+
+ async def run_experiment(self):
+ for model in self.models:
+ if self.debug:
+ print(f"Running experiment for model: {model}")
+
+ for iteration in range(1, self.iterations + 1):
+ game_agent = Proposer(amount=self.amount, model=model, temperature=self.temperature)
+ response = await game_agent.run()
+ if self.debug:
+ print(response)
+
+ # Utilisation de la notation point pour accéder aux attributs
+ my_share = response.my_share
+ other_share = response.other_share
+ reasoning = response.reasoning.replace('"', '""')
+
+ with open(self.output_file, 'a', encoding='utf-8') as f:
+ f.write(f'{iteration},{model},{self.temperature},{self.amount},{my_share},{other_share},"{reasoning}"\n')
+
+
+if __name__ == "__main__":
+ models = ["qwen3"]
+ # # "gpt-4.5-preview-2025-02-27" "llama3", "mistral-small", "deepseek-r1", "qwen3", "mixtral:8x7b", "llama3.3:latest", "deepseek-r1:7b"
+ temperature = 0.7
+ amount = 100
+ iterations = 30
+ output_file = '../../data/ultimatum/proposer.csv'
+
+ experiment = UltimatumExperiment(models=models, temperature=temperature, amount=amount, iterations=iterations, output_file=output_file)
+
+ asyncio.run(experiment.run_experiment())
+ print(f"Experiment results saved to {output_file}")
\ No newline at end of file
--
GitLab