{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/flatten-lists","entry":"flatten_lists","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":9,"n_papers_ran":9,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2306.03034","paper":"/paper/tackling-cooperative-incompatibility-for-zero","title":"Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"2208.04957","paper":"/paper/heterogeneous-multi-agent-zero-shot","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","date":"2022-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"2007.08459","paper":"/paper/pc-pg-policy-cover-directed-exploration-for","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","date":"2020-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1910.03857","paper":"/paper/policy-optimization-through-approximated","title":"Policy Optimization Through Approximate Importance Sampling","date":"2019-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marctom/POTAIS","path":"algorithm.py","file_url":"https://github.com/marctom/POTAIS/blob/HEAD/algorithm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1909.12995","paper":"/paper/learning-fast-adaptation-with-meta-strategy","title":"Learning Fast Adaptation with Meta Strategy Optimization","date":"2019-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1905.09191","paper":"/paper/learning-robust-options-by-conditional-value","title":"Learning Robust Options by Conditional Value at Risk Optimization","date":"2019-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization","path":"LearningMoreRobustOption/pposgd_simple.py","file_url":"https://github.com/TakuyaHiraoka/Learning-Robust-Options-by-Conditional-Value-at-Risk-Optimization/blob/HEAD/LearningMoreRobustOption/pposgd_simple.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1801.01432","paper":"/paper/jointly-learning-to-construct-and-control","title":"Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1703.02702","paper":"/paper/robust-adversarial-reinforcement-learning","title":"Robust Adversarial Reinforcement Learning","date":"2017-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jekyll1021/RARL","path":"reimplementation/PPO_RARL.py","file_url":"https://github.com/Jekyll1021/RARL/blob/HEAD/reimplementation/PPO_RARL.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}},{"arxiv_id":"1606.03476","paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bukysun/gail-traj-eb","path":"gailtf/algo/trpo_mpi.py","file_url":"https://github.com/bukysun/gail-traj-eb/blob/HEAD/gailtf/algo/trpo_mpi.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0173e4280d9a9884","mcp_get_code":{"code_sha256":"0173e4280d9a9884"}}]}