{"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-metric","entry":"eval_metric","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":3,"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":3,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":1,"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":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"olgarithmics/ICLR_CAMIL","path":"models/metrics.py","file_url":"https://github.com/olgarithmics/ICLR_CAMIL/blob/HEAD/models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d0f65012732e719","mcp_get_code":{"code_sha256":"6d0f65012732e719"}},{"arxiv_id":"2403.04086","paper":"/paper/automated-multi-task-learning-for-joint","title":"Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sh-src/autodp","path":"utils/experiments.py","file_url":"https://github.com/sh-src/autodp/blob/HEAD/utils/experiments.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd44d9862276aecb","mcp_get_code":{"code_sha256":"cd44d9862276aecb"}},{"arxiv_id":"2109.14509","paper":"/paper/pac-bayes-information-bottleneck","title":"PAC-Bayes Information Bottleneck","date":"2021-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryanwangzf/pac-bayes-ib","path":"src/pib_utils.py","file_url":"https://github.com/ryanwangzf/pac-bayes-ib/blob/HEAD/src/pib_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2137b2a6d2e103c","mcp_get_code":{"code_sha256":"e2137b2a6d2e103c"}},{"arxiv_id":"2102.09492","paper":"/paper/optimizing-black-box-metrics-with-iterative","title":"Optimizing Black-box Metrics with Iterative Example Weighting","date":"2021-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"koyejolab/fweg","path":"utils/fweg.py","file_url":"https://github.com/koyejolab/fweg/blob/HEAD/utils/fweg.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be7432c5b8bf5e94","mcp_get_code":{"code_sha256":"be7432c5b8bf5e94"}},{"arxiv_id":"1406.3896","paper":"/paper/freeze-thaw-bayesian-optimization","title":"Freeze-Thaw Bayesian Optimization","date":"2014-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jamesrobertlloyd/automl-phase-2","path":"libscores.py","file_url":"https://github.com/jamesrobertlloyd/automl-phase-2/blob/HEAD/libscores.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1487ddd3cb7dcf54","mcp_get_code":{"code_sha256":"1487ddd3cb7dcf54"}}]}