{"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-performance","entry":"eval_performance","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":2,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":0,"unverified":2},"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":"2306.12941","paper":"/paper/robust-semantic-segmentation-strong","title":"Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models","date":"2023-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nmndeep/robust-segmentation","path":"tools/infer.py","file_url":"https://github.com/nmndeep/robust-segmentation/blob/HEAD/tools/infer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"655558caaffbbdad","mcp_get_code":{"code_sha256":"655558caaffbbdad"}},{"arxiv_id":"2302.11213","paper":"/paper/feasible-recourse-plan-via-diverse","title":"Feasible Recourse Plan via Diverse Interpolation","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"duykhuongnguyen/recourse-plan-diverse-interpolation","path":"train_model.py","file_url":"https://github.com/duykhuongnguyen/recourse-plan-diverse-interpolation/blob/HEAD/train_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1ced764d1edacf1","mcp_get_code":{"code_sha256":"a1ced764d1edacf1"}},{"arxiv_id":"1901.08129","paper":"/paper/the-multi-agent-reinforcement-learning-in","title":"The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition","date":"2019-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crowdAI/marLo","path":"marlo/experiments/evaluator.py","file_url":"https://github.com/crowdAI/marLo/blob/HEAD/marlo/experiments/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9888ad094311172f","mcp_get_code":{"code_sha256":"9888ad094311172f"}},{"arxiv_id":"2023.findings-acl.657","paper":null,"title":"arXiv:2023.findings-acl.657","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"luka-group/MrCoD","path":"BERT+ATT_scripts/codred-blend.py","file_url":"https://github.com/luka-group/MrCoD/blob/HEAD/BERT%2BATT_scripts/codred-blend.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"881fa8580b7af085","mcp_get_code":{"code_sha256":"881fa8580b7af085"}},{"arxiv_id":"2021.emnlp-main.366","paper":null,"title":"arXiv:2021.emnlp-main.366","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thunlp/CodRED","path":"baseline/codred-blend/codred-blend.py","file_url":"https://github.com/thunlp/CodRED/blob/HEAD/baseline/codred-blend/codred-blend.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"881fa8580b7af085","mcp_get_code":{"code_sha256":"881fa8580b7af085"}}]}