{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/classifier-calibration","name":"Classifier calibration","slug":"classifier-calibration","description_markdown":"Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. The two common calibration metrics are Expected Calibration Error (ECE) and Maximum Calibration Error (MCE).","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":19,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/classifier-calibration-on-cifar-100","slug":"classifier-calibration-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":1,"metrics":["Expected Calibration Error"],"first_row_in_archive_order":{"model":"R-Mix (PreActResNet-18)","paper_title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","paper_url":"/paper/expeditious-saliency-guided-mix-up-through","paper_date":"2022-12-09","arxiv_id":"2212.04875","code_links":[{"title":"minhlong94/random-mixup","url":"https://github.com/minhlong94/random-mixup"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045}],"subtasks":[],"parent_tasks":[{"url":"/task/classification-1","name":"Classification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":29,"of":29,"of_with_code":19,"tagged_in_all":29,"counts":{"archive_papers_tagged":29,"with_a_code_link":19,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":29,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/masksembles-for-uncertainty-estimation","slug":"masksembles-for-uncertainty-estimation","title":"Masksembles for Uncertainty Estimation","date":"2020-12-15","arxiv_id":"2012.08334","repositories_listed":4,"syntology":null},{"url":"/paper/no-fear-of-heterogeneity-classifier","slug":"no-fear-of-heterogeneity-classifier","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","date":"2021-06-09","arxiv_id":"2106.05001","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/no-fear-of-heterogeneity-classifier#ran","syntology_url":"https://syntology.ai/paper/2106.05001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05001"}},"official":null}},{"url":"/paper/preprompt-predictive-prompting-for-class","slug":"preprompt-predictive-prompting-for-class","title":"PrePrompt: Predictive prompting for class incremental learning","date":"2025-05-13","arxiv_id":"2505.08586","repositories_listed":1,"syntology":null},{"url":"/paper/long-tailed-medical-diagnosis-with-relation","slug":"long-tailed-medical-diagnosis-with-relation","title":"Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration","date":"2025-02-05","arxiv_id":"2502.03238","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-generalized-few-shot-semantic","slug":"enhancing-generalized-few-shot-semantic","title":"Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer","date":"2024-12-20","arxiv_id":"2412.15835","repositories_listed":1,"syntology":null},{"url":"/paper/improved-user-identification-through","slug":"improved-user-identification-through","title":"Improved User Identification through Calibrated Monte-Carlo Dropout","date":"2024-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/accuracy-preserving-calibration-via","slug":"accuracy-preserving-calibration-via","title":"Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex","date":"2024-02-21","arxiv_id":"2402.13765","repositories_listed":1,"syntology":null},{"url":"/paper/no-fear-of-classifier-biases-neural-collapse","slug":"no-fear-of-classifier-biases-neural-collapse","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","date":"2023-03-17","arxiv_id":"2303.10058","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/no-fear-of-classifier-biases-neural-collapse#ran","syntology_url":"https://syntology.ai/paper/2303.10058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10058"}},"official":{"repos":["zexilee/iccv-2023-fedetf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expeditious-saliency-guided-mix-up-through","slug":"expeditious-saliency-guided-mix-up-through","title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","date":"2022-12-09","arxiv_id":"2212.04875","repositories_listed":1,"syntology":null},{"url":"/paper/fedfa-federated-learning-with-feature-anchors","slug":"fedfa-federated-learning-with-feature-anchors","title":"FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data","date":"2022-11-17","arxiv_id":"2211.09299","repositories_listed":1,"syntology":null},{"url":"/paper/packed-ensembles-for-efficient-uncertainty","slug":"packed-ensembles-for-efficient-uncertainty","title":"Packed-Ensembles for Efficient Uncertainty Estimation","date":"2022-10-17","arxiv_id":"2210.09184","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/packed-ensembles-for-efficient-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2210.09184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09184"}},"official":{"repos":["ENSTA-U2IS-AI/torch-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/class-wise-and-reduced-calibration-methods","slug":"class-wise-and-reduced-calibration-methods","title":"Class-wise and reduced calibration methods","date":"2022-10-07","arxiv_id":"2210.03702","repositories_listed":1,"syntology":null},{"url":"/paper/hidden-heterogeneity-when-to-choose","slug":"hidden-heterogeneity-when-to-choose","title":"Hidden Heterogeneity: When to Choose Similarity-Based Calibration","date":"2022-02-03","arxiv_id":"2202.01840","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-and-incremental-few-shot-learning","slug":"generalized-and-incremental-few-shot-learning","title":"Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting","date":"2021-08-18","arxiv_id":"2108.08165","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":3,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generalized-and-incremental-few-shot-learning#ran","syntology_url":"https://syntology.ai/paper/2108.08165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08165"}},"official":{"repos":["annusha/lcwof"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/danish-fungi-2020-not-just-another-image","slug":"danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","repositories_listed":1,"syntology":null},{"url":"/paper/classifier-calibration-with-implications-to","slug":"classifier-calibration-with-implications-to","title":"Classifier Calibration: with application to threat scores in cybersecurity","date":"2021-02-09","arxiv_id":"2102.05143","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-do-self-supervised-models-transfer","slug":"how-well-do-self-supervised-models-transfer","title":"How Well Do Self-Supervised Models Transfer?","date":"2020-11-26","arxiv_id":"2011.13377","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-well-do-self-supervised-models-transfer#ran","syntology_url":"https://syntology.ai/paper/2011.13377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13377"}},"official":{"repos":["linusericsson/ssl-transfer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multivariate-confidence-calibration-for","slug":"multivariate-confidence-calibration-for","title":"Multivariate Confidence Calibration for Object Detection","date":"2020-04-28","arxiv_id":"2004.13546","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multivariate-confidence-calibration-for#ran","syntology_url":"https://syntology.ai/paper/2004.13546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13546"}},"official":{"repos":["fabiankueppers/calibration-framework"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-class-probabilistic-classification","slug":"multi-class-probabilistic-classification","title":"Multi-class probabilistic classification using inductive and cross Venn-Abers predictors","date":"2017-06-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"fedsa-a-unified-representation-learning-via","title":"FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning","date":"2025-01-09","arxiv_id":"2501.05496","repositories_listed":0,"syntology":null},{"url":"/paper/decoupling-decision-making-in-fraud","slug":"decoupling-decision-making-in-fraud","title":"Decoupling Decision-Making in Fraud Prevention through Classifier Calibration for Business Logic Action","date":"2024-01-10","arxiv_id":"2401.05240","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-calibration-with-roc-regularized","title":"Classifier Calibration with ROC-Regularized Isotonic Regression","date":"2023-11-21","arxiv_id":"2311.12436","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-your-metric-telling-you-evaluating","title":"What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability","date":"2022-05-23","arxiv_id":"2205.11454","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-calibration-how-to-assess-and","title":"Classifier Calibration: A survey on how to assess and improve predicted class probabilities","date":"2021-12-20","arxiv_id":"2112.10327","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-classifier-calibration-for-small-data","title":"Better Classifier Calibration for Small Data Sets","date":"2020-02-24","arxiv_id":"2002.10199","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-frequency-residual-learning-for-multi","title":"High Frequency Residual Learning for Multi-Scale Image Classification","date":"2019-05-07","arxiv_id":"1905.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-classifier-calibration-using-an","title":"Binary Classifier Calibration using an Ensemble of Near Isotonic Regression Models","date":"2015-11-16","arxiv_id":"1511.05191","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-classifier-calibration-non-parametric","title":"Binary Classifier Calibration: Non-parametric approach","date":"2014-01-14","arxiv_id":"1401.3390","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-classifier-calibration-bayesian-non","title":"Binary Classifier Calibration: Bayesian Non-Parametric Approach","date":"2014-01-13","arxiv_id":"1401.2955","repositories_listed":0,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/classifier-calibration/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/classifier-calibration/papers/ran/1","json":"/task/classifier-calibration/papers/ran/1.json","rows":6}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ad5f4249d0ffa5febb8daa3cf78b776531696a19795127ffe4d4e66a4bc1e47e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}