{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FAVMIKTSXOL4QTKBRTTODEVZOO","short_pith_number":"pith:FAVMIKTS","schema_version":"1.0","canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","source":{"kind":"arxiv","id":"1906.07337","version":1},"attestation_state":"computed","paper":{"title":"Measuring Bias in Contextualized Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Ayush Pareek, Keita Kurita, Nidhi Vyas, Yulia Tsvetkov","submitted_at":"2019-06-18T01:58:56Z","abstract_excerpt":"Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.07337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"7c3ba3446021a9828a81382313277793fea93ace9317288d7e2f20274fcf93a7","abstract_canon_sha256":"e61bd4e3066c1560f48323ea602d0454a5c3a90c20a51ff7dd45fba79a5b8d06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.164595Z","signature_b64":"hVWshWZc+aL1YuRqsh5ixCu648sqSwJa006cV8HK2o612bwjPKbTweq2+/5YPoZ+qHNRe/wcgMBYAZr1WGEEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","last_reissued_at":"2026-05-17T23:43:08.163845Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.163845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Bias in Contextualized Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Ayush Pareek, Keita Kurita, Nidhi Vyas, Yulia Tsvetkov","submitted_at":"2019-06-18T01:58:56Z","abstract_excerpt":"Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07337","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.07337","created_at":"2026-05-17T23:43:08.163968+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07337v1","created_at":"2026-05-17T23:43:08.163968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07337","created_at":"2026-05-17T23:43:08.163968+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAVMIKTSXOL4","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAVMIKTSXOL4QTKB","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAVMIKTS","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2209.07858","citing_title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2112.04359","citing_title":"Ethical and social risks of harm from Language Models","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04127","citing_title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO","json":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO.json","graph_json":"https://pith.science/api/pith-number/FAVMIKTSXOL4QTKBRTTODEVZOO/graph.json","events_json":"https://pith.science/api/pith-number/FAVMIKTSXOL4QTKBRTTODEVZOO/events.json","paper":"https://pith.science/paper/FAVMIKTS"},"agent_actions":{"view_html":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO","download_json":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO.json","view_paper":"https://pith.science/paper/FAVMIKTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07337&json=true","fetch_graph":"https://pith.science/api/pith-number/FAVMIKTSXOL4QTKBRTTODEVZOO/graph.json","fetch_events":"https://pith.science/api/pith-number/FAVMIKTSXOL4QTKBRTTODEVZOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/action/storage_attestation","attest_author":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/action/author_attestation","sign_citation":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/action/citation_signature","submit_replication":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/action/replication_record"}},"created_at":"2026-05-17T23:43:08.163968+00:00","updated_at":"2026-05-17T23:43:08.163968+00:00"}