{"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/reliability-diagram","entry":"reliability_diagram","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":1,"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":1,"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":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":"2605.29380","paper":"/paper/arxiv-2605-29380","title":"TRACER: Persistent Regularization for Robust Multimodal Finetuning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"HesamAsad/TRACER","path":"src/visualize.py","file_url":"https://github.com/HesamAsad/TRACER/blob/HEAD/src/visualize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d558de6dd71f4220","mcp_get_code":{"code_sha256":"d558de6dd71f4220"}},{"arxiv_id":"2311.09118","paper":"/paper/wildlifedatasets-an-open-source-toolkit-for","title":"WildlifeDatasets: An open-source toolkit for animal re-identification","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wildlifedatasets/wildlife-tools","path":"wildlife_tools/similarity/calibration.py","file_url":"https://github.com/wildlifedatasets/wildlife-tools/blob/HEAD/wildlife_tools/similarity/calibration.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85d8fa6026cd258d","mcp_get_code":{"code_sha256":"85d8fa6026cd258d"}},{"arxiv_id":"2311.01723","paper":"/paper/towards-calibrated-robust-fine-tuning-of","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MLAI-Yonsei/CaRot","path":"src/visualize.py","file_url":"https://github.com/MLAI-Yonsei/CaRot/blob/HEAD/src/visualize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d558de6dd71f4220","mcp_get_code":{"code_sha256":"d558de6dd71f4220"}},{"arxiv_id":"2309.12236","paper":"/paper/smooth-ece-principled-reliability-diagrams","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-calibration","path":"src/relplot/diagrams.py","file_url":"https://github.com/apple/ml-calibration/blob/HEAD/src/relplot/diagrams.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fbf4374242d0bda7","mcp_get_code":{"code_sha256":"fbf4374242d0bda7"}},{"arxiv_id":"2104.00466","paper":"/paper/improving-calibration-for-long-tailed-1","title":"Improving Calibration for Long-Tailed Recognition","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jia-Research-Lab/MiSLAS","path":"reliability_diagrams.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/reliability_diagrams.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"722e0bb5cb9f0a0d","mcp_get_code":{"code_sha256":"722e0bb5cb9f0a0d"}}]}