{"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":"/paper/ai-fairness-360-an-extensible-toolkit-for","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","arxiv_id":"1810.01943","date":"2018-10-03","proceeding":null,"authors":["Rachel K. E. Bellamy","Kuntal Dey","Michael Hind","Samuel C. Hoffman","Stephanie Houde","Kalapriya Kannan","Pranay Lohia","Jacquelyn Martino","Sameep Mehta","Aleksandra Mojsilovic","Seema Nagar","Karthikeyan Natesan Ramamurthy","John Richards","Diptikalyan Saha","Prasanna Sattigeri","Moninder Singh","Kush R. Varshney","Yunfeng Zhang"],"abstract":"Fairness is an increasingly important concern as machine learning models are\nused to support decision making in high-stakes applications such as mortgage\nlending, hiring, and prison sentencing. This paper introduces a new open source\nPython toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released\nunder an Apache v2.0 license {https://github.com/ibm/aif360). The main\nobjectives of this toolkit are to help facilitate the transition of fairness\nresearch algorithms to use in an industrial setting and to provide a common\nframework for fairness researchers to share and evaluate algorithms.\n  The package includes a comprehensive set of fairness metrics for datasets and\nmodels, explanations for these metrics, and algorithms to mitigate bias in\ndatasets and models. It also includes an interactive Web experience\n(https://aif360.mybluemix.net) that provides a gentle introduction to the\nconcepts and capabilities for line-of-business users, as well as extensive\ndocumentation, usage guidance, and industry-specific tutorials to enable data\nscientists and practitioners to incorporate the most appropriate tool for their\nproblem into their work products. The architecture of the package has been\nengineered to conform to a standard paradigm used in data science, thereby\nfurther improving usability for practitioners. Such architectural design and\nabstractions enable researchers and developers to extend the toolkit with their\nnew algorithms and improvements, and to use it for performance benchmarking. A\nbuilt-in testing infrastructure maintains code quality.","url_abs":"http://arxiv.org/abs/1810.01943v1","url_pdf":"http://arxiv.org/pdf/1810.01943v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/IBM/AIF360","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/DaveFClarke/ml_bias_checking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/aradhanacha/aif360","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/bspanjers/AIFBAREND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/cesarojuliana/feature_importance_fairness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/chenzhenpeng18/biasmitigationstudy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/chenzhenpeng18/fse22-maat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/chenzhenpeng18/icse24-multi-attribute-fairness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/chenzhenpeng18/tosem23-biasmitigationstudy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/datalab-georgetown/fairness-and-missing-values","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/elsalmi/LendingClub","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/gitforreview/dsaa_journal_review","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ai-fairness-360-an-extensible-toolkit-for","repo_url":"https://github.com/marcinknara/520-ML-DevToolKit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.01943","atlas_url":"https://app.syntology.ai/?focus=1810.01943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.01943"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gitforreview/dsaa_journal_review","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marcinknara/520-ML-DevToolKit","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenzhenpeng18/biasmitigationstudy","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/elsalmi/LendingClub","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bspanjers/AIFBAREND","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenzhenpeng18/fse22-maat","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aradhanacha/aif360","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenzhenpeng18/icse24-multi-attribute-fairness","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DaveFClarke/ml_bias_checking","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/AIF360","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenzhenpeng18/tosem23-biasmitigationstudy","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cesarojuliana/feature_importance_fairness","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/datalab-georgetown/fairness-and-missing-values","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":2,"unverified":8},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":7,"ran":3,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"eede2c40a6ec49b1","entry":"default_preprocessing","repo":"datalab-georgetown/fairness-and-missing-values","repo_kind":"listed","path":"MAR_compas.py","file_url":"https://github.com/datalab-georgetown/fairness-and-missing-values/blob/HEAD/MAR_compas.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eede2c40a6ec49b1"}},{"code_sha256_prefix":"3121e31a3851b066","entry":"get_distortion_adult","repo":"datalab-georgetown/fairness-and-missing-values","repo_kind":"listed","path":"MNAR_adult.py","file_url":"https://github.com/datalab-georgetown/fairness-and-missing-values/blob/HEAD/MNAR_adult.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3121e31a3851b066"}},{"code_sha256_prefix":"2c079b2e82f2279d","entry":"get_distortion_compas","repo":"datalab-georgetown/fairness-and-missing-values","repo_kind":"listed","path":"MAR_compas.py","file_url":"https://github.com/datalab-georgetown/fairness-and-missing-values/blob/HEAD/MAR_compas.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c079b2e82f2279d"}},{"code_sha256_prefix":"289eb0c6849d3227","entry":"do_decorate","repo":"IBM/AIF360","repo_kind":"official","path":"aif360/decorating_metaclass.py","file_url":"https://github.com/IBM/AIF360/blob/HEAD/aif360/decorating_metaclass.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"289eb0c6849d3227"}},{"code_sha256_prefix":"01ea0d2b717db869","entry":"dont_decorate","repo":"IBM/AIF360","repo_kind":"official","path":"aif360/decorating_metaclass.py","file_url":"https://github.com/IBM/AIF360/blob/HEAD/aif360/decorating_metaclass.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01ea0d2b717db869"}},{"code_sha256_prefix":"def3932f5d378389","entry":"factory","repo":"IBM/AIF360","repo_kind":"official","path":"aif360/decorating_metaclass.py","file_url":"https://github.com/IBM/AIF360/blob/HEAD/aif360/decorating_metaclass.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"def3932f5d378389"}},{"code_sha256_prefix":"1533d1dc758fbfbb","entry":"get_distortion_syn","repo":"gitforreview/dsaa_journal_review","repo_kind":"listed","path":"MNAR_syn.py","file_url":"https://github.com/gitforreview/dsaa_journal_review/blob/HEAD/MNAR_syn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1533d1dc758fbfbb"}},{"code_sha256_prefix":"557b4e0443b49c81","entry":"quantizeLOS","repo":"gitforreview/dsaa_journal_review","repo_kind":"listed","path":"MNAR_syn.py","file_url":"https://github.com/gitforreview/dsaa_journal_review/blob/HEAD/MNAR_syn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"557b4e0443b49c81"}},{"code_sha256_prefix":"ede92860076c393d","entry":"quantizePrior1","repo":"gitforreview/dsaa_journal_review","repo_kind":"listed","path":"MNAR_syn.py","file_url":"https://github.com/gitforreview/dsaa_journal_review/blob/HEAD/MNAR_syn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ede92860076c393d"}},{"code_sha256_prefix":"1e900bae8b2c9e29","entry":"weighted_cost","repo":"IBM/AIF360","repo_kind":"official","path":"aif360/algorithms/postprocessing/calibrated_eq_odds_postprocessing.py","file_url":"https://github.com/IBM/AIF360/blob/HEAD/aif360/algorithms/postprocessing/calibrated_eq_odds_postprocessing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e900bae8b2c9e29"}},{"code_sha256_prefix":"7fb981da51078eff","entry":"weighted_cost","repo":"DaveFClarke/ml_bias_checking","repo_kind":"listed","path":"aif360/algorithms/postprocessing/calibrated_eq_odds_postprocessing.py","file_url":"https://github.com/DaveFClarke/ml_bias_checking/blob/HEAD/aif360/algorithms/postprocessing/calibrated_eq_odds_postprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7fb981da51078eff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}