{"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/eval-actor","entry":"eval_actor","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":5,"n_papers_ran":5,"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":5,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"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":"2406.11978","paper":"/paper/dialogue-action-tokens-steering-language","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likenneth/dialogue_action_token","path":"dat/pre_bc.py","file_url":"https://github.com/likenneth/dialogue_action_token/blob/HEAD/dat/pre_bc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca55c2bc3a455a58","mcp_get_code":{"code_sha256":"ca55c2bc3a455a58"}},{"arxiv_id":"2405.16907","paper":"/paper/gta-generative-trajectory-augmentation-with","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conglu1997/SynthER","path":"synther/corl/algorithms/edac.py","file_url":"https://github.com/conglu1997/SynthER/blob/HEAD/synther/corl/algorithms/edac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ca0a51383f3d84b","mcp_get_code":{"code_sha256":"7ca0a51383f3d84b"}},{"arxiv_id":"2405.06192","paper":"/paper/contrastive-representation-for-data-filtering","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"battlewen/igdf","path":"algorithms/igdf/igdf_o2o.py","file_url":"https://github.com/battlewen/igdf/blob/HEAD/algorithms/igdf/igdf_o2o.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cef315eeed246be2","mcp_get_code":{"code_sha256":"cef315eeed246be2"}},{"arxiv_id":"2310.14550","paper":"/paper/corruption-robust-offline-reinforcement-2","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangrui2015/uwmsg","path":"UWMSG.py","file_url":"https://github.com/yangrui2015/uwmsg/blob/HEAD/UWMSG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"433fa11651ba0f09","mcp_get_code":{"code_sha256":"433fa11651ba0f09"}},{"arxiv_id":"2309.16973","paper":"/paper/towards-robust-offline-to-online","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"battlewen/ro2o","path":"algorithms/finetune/ro2o_ft_ant_LCB.py","file_url":"https://github.com/battlewen/ro2o/blob/HEAD/algorithms/finetune/ro2o_ft_ant_LCB.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26dee61e902bf417","mcp_get_code":{"code_sha256":"26dee61e902bf417"}}]}