{"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/expected-calibration-error","entry":"expected_calibration_error","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":12,"n_papers_ran":7,"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":11,"n_samples_ran":7,"n_samples_fingerprinted":2,"n_places":12,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":0,"ran":5,"unverified":4},"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":"2608.18919","paper":"/paper/arxiv-2608-18919","title":"Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"perpetual-ml/perpetual","path":"package-python/python/perpetual/booster.py","file_url":"https://github.com/perpetual-ml/perpetual/blob/HEAD/package-python/python/perpetual/booster.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":"86ccec269a6282b2","mcp_get_code":{"code_sha256":"86ccec269a6282b2"}},{"arxiv_id":"2501.05040","paper":"/paper/swe-fixer-training-open-source-llms-for","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","date":"2025-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jorge-martinez-gil/graphcodebert-feature-integration","path":"src/featfuse/metrics.py","file_url":"https://github.com/jorge-martinez-gil/graphcodebert-feature-integration/blob/HEAD/src/featfuse/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dc062f89cd64e1d","mcp_get_code":{"code_sha256":"4dc062f89cd64e1d"}},{"arxiv_id":"2411.02988","paper":"/paper/confidence-calibration-of-classifiers-with","title":"Confidence Calibration of Classifiers with Many Classes","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mominabbass/LinC","path":"utils.py","file_url":"https://github.com/mominabbass/LinC/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc60c15158733e34","mcp_get_code":{"code_sha256":"dc60c15158733e34"}},{"arxiv_id":"2406.17746","paper":"/paper/recite-reconstruct-recollect-memorization-in","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/semantic-memorization","path":"model_utils.py","file_url":"https://github.com/eleutherai/semantic-memorization/blob/HEAD/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"736b3b9ab49b28d1","mcp_get_code":{"code_sha256":"736b3b9ab49b28d1"}},{"arxiv_id":"2403.15567","paper":"/paper/do-not-trust-what-you-trust-miscalibration-in","title":"Do not trust what you trust: Miscalibration in Semi-supervised Learning","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shambhavicodes/miscalibration-ssl","path":"metrics.py","file_url":"https://github.com/shambhavicodes/miscalibration-ssl/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2249c8712edfa8ce","mcp_get_code":{"code_sha256":"2249c8712edfa8ce"}},{"arxiv_id":"2402.10373","paper":"/paper/biomistral-a-collection-of-open-source","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"biomistral/biomistral","path":"Evaluation/ECE/StudyCalibration-Langs.py","file_url":"https://github.com/biomistral/biomistral/blob/HEAD/Evaluation/ECE/StudyCalibration-Langs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"36c5a555be75ec7b","mcp_get_code":{"code_sha256":"36c5a555be75ec7b"}},{"arxiv_id":"2401.12406","paper":"/paper/enhancing-in-context-learning-via-linear","title":"Enhancing In-context Learning via Linear Probe Calibration","date":"2024-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mominabbass/linc","path":"utils.py","file_url":"https://github.com/mominabbass/linc/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc60c15158733e34","mcp_get_code":{"code_sha256":"dc60c15158733e34"}},{"arxiv_id":"2310.14564","paper":"/paper/language-models-hallucinate-but-may-excel-at","title":"Language Models Hallucinate, but May Excel at Fact Verification","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianguanthu/llmforfv","path":"code/metric.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"241c78299ce539d4","mcp_get_code":{"code_sha256":"241c78299ce539d4"}},{"arxiv_id":"2206.01934","paper":"/paper/stochastic-multiple-target-sampling-gradient","title":"Stochastic Multiple Target Sampling Gradient Descent","date":"2022-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"viethoang1512/mt-sgd","path":"celeba/multi_task/train_mt_sgd.py","file_url":"https://github.com/viethoang1512/mt-sgd/blob/HEAD/celeba/multi_task/train_mt_sgd.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"46e47135d4d407b3","mcp_get_code":{"code_sha256":"46e47135d4d407b3"}},{"arxiv_id":"2105.13937","paper":"/paper/polygonal-unadjusted-langevin-algorithms","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DongyoungLim/THEO_POULA","path":"metrics_ilb.py","file_url":"https://github.com/DongyoungLim/THEO_POULA/blob/HEAD/metrics_ilb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9fca78c7f571171f","mcp_get_code":{"code_sha256":"9fca78c7f571171f"}},{"arxiv_id":"1912.03263","paper":"/paper/your-classifier-is-secretly-an-energy-based-1","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","date":"2019-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divymurli/ML_Reprod_HybridEnergyModels","path":"calibration.py","file_url":"https://github.com/divymurli/ML_Reprod_HybridEnergyModels/blob/HEAD/calibration.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f58aff46d12bb096","mcp_get_code":{"code_sha256":"f58aff46d12bb096"}},{"arxiv_id":"1903.01610","paper":"/paper/the-vulnerabilities-of-graph-convolutional","title":"Adversarial Examples on Graph Data: Deep Insights into Attack and Defense","date":"2019-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stellargraph/stellargraph","path":"stellargraph/calibration.py","file_url":"https://github.com/stellargraph/stellargraph/blob/HEAD/stellargraph/calibration.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":"c2b35b0171ab08d5","mcp_get_code":{"code_sha256":"c2b35b0171ab08d5"}}]}