aamas-reproducibility

1# AAMAS Reproducibility
2 
3Use this before submission and again before camera-ready. The reproducibility question at AAMAS
4is not only "can I rerun the model" but "can I reproduce the *interaction* - the same agents,
5the same game, the same emergent outcome."
6 
7## Evidence map
8 
9- Map each theorem, mechanism property, convergence claim, and empirical interaction claim to a
10  verifiable location in the paper, appendix, supplement, or artifact.
11- For theory, state the game, the information structure, the solution concept, assumptions,
12  proof dependencies, and failure modes clearly enough for a game theorist.
13- For experiments, report the environment, number of agents, opponent/population set, training
14  regime, evaluation opponents, metrics, hyperparameter ranges, chosen settings, seeds,
15  repeated runs, compute, and runtime.
16- For small or noisy strategic differences, add uncertainty: standard errors, confidence
17  intervals, or paired tests over seeds and over opponents.
18- Explain any missing code or environment honestly, and describe how a reader could reproduce
19  the interaction in principle.
20- Keep the artifact consistent with the paper; a claim the artifact cannot demonstrate is a
21  review-risk multiplier.
22 
23## Claim-to-evidence audit table
24 
25| Claim | Pure-theory answer | Learning-plus-game answer |
26|---|---|---|
27| Solution concept reached | Proof with the game and information structure stated | Plus convergence curves under other agents' adaptation |
28…