{"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/bias-in-bios-a-case-study-of-semantic","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","arxiv_id":"1901.09451","date":"2019-01-27","proceeding":null,"authors":["Maria De-Arteaga","Alexey Romanov","Hanna Wallach","Jennifer Chayes","Christian Borgs","Alexandra Chouldechova","Sahin Geyik","Krishnaram Kenthapadi","Adam Tauman Kalai"],"abstract":"We present a large-scale study of gender bias in occupation classification, a\ntask where the use of machine learning may lead to negative outcomes on\npeoples' lives. We analyze the potential allocation harms that can result from\nsemantic representation bias. To do so, we study the impact on occupation\nclassification of including explicit gender indicators---such as first names\nand pronouns---in different semantic representations of online biographies.\nAdditionally, we quantify the bias that remains when these indicators are\n\"scrubbed,\" and describe proxy behavior that occurs in the absence of explicit\ngender indicators. As we demonstrate, differences in true positive rates\nbetween genders are correlated with existing gender imbalances in occupations,\nwhich may compound these imbalances.","url_abs":"http://arxiv.org/abs/1901.09451v1","url_pdf":"http://arxiv.org/pdf/1901.09451v1.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":"bias-in-bios-a-case-study-of-semantic","repo_url":"https://github.com/Shaul1321/nullspace_projection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bias-in-bios-a-case-study-of-semantic","repo_url":"https://github.com/jasonshaoshun/SAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bias-in-bios-a-case-study-of-semantic","repo_url":"https://github.com/maxwellyin/mabr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"bias-in-bios-a-case-study-of-semantic","repo_url":"https://github.com/shauli-ravfogel/nullspace_projection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bias-in-bios-a-case-study-of-semantic","repo_url":"https://github.com/technion-cs-nlp/blind","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[{"slug":"biasbios","name":"BiasBios","full_name":"Bias in Bios"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.09451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09451"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/technion-cs-nlp/blind","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxwellyin/mabr","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Shaul1321/nullspace_projection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jasonshaoshun/SAL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shauli-ravfogel/nullspace_projection","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":10},"by_repo_kind":{"listed":{"samples":12,"ran":2,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"6603d34965799b5d","entry":"get_projection_to_intersection_of_nullspaces","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/debias.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6603d34965799b5d"}},{"code_sha256_prefix":"109a64c49d7364c5","entry":"get_rowspace_projection","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/debias.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"109a64c49d7364c5"}},{"code_sha256_prefix":"3b1da49bcea7e00a","entry":"debias_by_specific_directions","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/debias.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":"3b1da49bcea7e00a"}},{"code_sha256_prefix":"06f4800d560a810f","entry":"debias_by_specific_directions","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/old_debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/old_debias.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":"06f4800d560a810f"}},{"code_sha256_prefix":"498cab078c78b4ed","entry":"debias_by_specific_directions","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/inlp-oop/inlp.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/inlp-oop/inlp.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":"498cab078c78b4ed"}},{"code_sha256_prefix":"b2e1ce12869f94c1","entry":"get_nullspace_projection","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/old_debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/old_debias.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":"b2e1ce12869f94c1"}},{"code_sha256_prefix":"7dc087e0a95da7ed","entry":"get_projection_to_intersection_of_nullspaces","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/inlp-oop/inlp.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/inlp-oop/inlp.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":"7dc087e0a95da7ed"}},{"code_sha256_prefix":"a702eb9853b92ca4","entry":"get_rowspace_projection","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/inlp-oop/inlp.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/inlp-oop/inlp.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":"a702eb9853b92ca4"}},{"code_sha256_prefix":"a604bbf3e7962f40","entry":"load_data","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/deepmoji/deepmoji_debias.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/deepmoji/deepmoji_debias.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":"a604bbf3e7962f40"}},{"code_sha256_prefix":"2aa0eb52d444e053","entry":"pairwise_distances","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/inlp-oop/triplet_loss.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/inlp-oop/triplet_loss.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":"2aa0eb52d444e053"}},{"code_sha256_prefix":"1299f5fff0c8311f","entry":"read_data_file","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/deepmoji/last_layer_extraction.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/deepmoji/last_layer_extraction.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":"1299f5fff0c8311f"}},{"code_sha256_prefix":"6c65e2e967eea2d2","entry":"transform_vec","repo":"shauli-ravfogel/nullspace_projection","repo_kind":"listed","path":"src/deepmoji/last_layer_extraction.py","file_url":"https://github.com/shauli-ravfogel/nullspace_projection/blob/HEAD/src/deepmoji/last_layer_extraction.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":"6c65e2e967eea2d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}