{"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/evaluate-one","entry":"evaluate_one","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":5,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":3},"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":"2606.01301","paper":"/paper/arxiv-2606-01301","title":"Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"yimingliao-blad/med-heal","path":"src/pre_atom/legacy/pilot_12_ra_icl/evaluate_fullscale_pilot12.py","file_url":"https://github.com/yimingliao-blad/med-heal/blob/HEAD/src/pre_atom/legacy/pilot_12_ra_icl/evaluate_fullscale_pilot12.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b38b8b67b3db5da2","mcp_get_code":{"code_sha256":"b38b8b67b3db5da2"}},{"arxiv_id":"2205.15124","paper":"/paper/generalizing-hierarchical-bayesian-bandits","title":"Mixed-Effect Thompson Sampling","date":"2022-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imadaouali/mixed-effect-thompson-sampling","path":"bandits/evaluation.py","file_url":"https://github.com/imadaouali/mixed-effect-thompson-sampling/blob/HEAD/bandits/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"abca9a6ba36d9e55","mcp_get_code":{"code_sha256":"abca9a6ba36d9e55"}},{"arxiv_id":"2005.08104","paper":"/paper/single-stage-semantic-segmentation-from-image","title":"Single-Stage Semantic Segmentation from Image Labels","date":"2020-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visinf/1-stage-wseg","path":"eval_seg.py","file_url":"https://github.com/visinf/1-stage-wseg/blob/HEAD/eval_seg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"604b797b42d81e92","mcp_get_code":{"code_sha256":"604b797b42d81e92"}},{"arxiv_id":"1910.04928","paper":"/paper/old-dog-learns-new-tricks-randomized-ucb-for","title":"Old Dog Learns New Tricks: Randomized UCB for Bandit Problems","date":"2019-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vaswanis/randucb","path":"MAB.py","file_url":"https://github.com/vaswanis/randucb/blob/HEAD/MAB.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4d71f5b15c873567","mcp_get_code":{"code_sha256":"4d71f5b15c873567"}},{"arxiv_id":"1805.09817","paper":"/paper/stereo-magnification-learning-view-synthesis","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","date":"2018-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/stereo-magnification","path":"evaluate.py","file_url":"https://github.com/google/stereo-magnification/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"48832df2ac8ef7ff","mcp_get_code":{"code_sha256":"48832df2ac8ef7ff"}}]}