{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JRZRKXK24H67FRR2GGW2XY6IHJ","short_pith_number":"pith:JRZRKXK2","schema_version":"1.0","canonical_sha256":"4c73155d5ae1fdf2c63a31adabe3c83a7d2a5aa7838d7680f01948a2c2f3e8f1","source":{"kind":"arxiv","id":"2109.03858","version":2},"attestation_state":"computed","paper":{"title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriel Stanovsky, Koren Lazar, Shahar Levy","submitted_at":"2021-09-08T18:14:11Z","abstract_excerpt":"Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manual"},"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":"2109.03858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T18:14:11Z","cross_cats_sorted":[],"title_canon_sha256":"42834cfc951e9fb03e3d39d7b831c70f4e659ddaa9d769091fb1caefcbcb2fa8","abstract_canon_sha256":"1e2dab671fa82225c3c4480058efbc0834ed4d14901c9a8daee3d1f5aecb1346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:06.119500Z","signature_b64":"SHPbHEhXSvzWqm9LmVl5I4bMXMm1j6mZeFJL5H40mpGYo0/zyl1V3AFIz+iJHJKC8vk8q29YRS+eSa5z8z2qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c73155d5ae1fdf2c63a31adabe3c83a7d2a5aa7838d7680f01948a2c2f3e8f1","last_reissued_at":"2026-07-05T03:13:06.119034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:06.119034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriel Stanovsky, Koren Lazar, Shahar Levy","submitted_at":"2021-09-08T18:14:11Z","abstract_excerpt":"Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03858","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.03858/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2109.03858","created_at":"2026-07-05T03:13:06.119086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03858v2","created_at":"2026-07-05T03:13:06.119086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03858","created_at":"2026-07-05T03:13:06.119086+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRZRKXK24H67","created_at":"2026-07-05T03:13:06.119086+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRZRKXK24H67FRR2","created_at":"2026-07-05T03:13:06.119086+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRZRKXK2","created_at":"2026-07-05T03:13:06.119086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07111","citing_title":"Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ","json":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ.json","graph_json":"https://pith.science/api/pith-number/JRZRKXK24H67FRR2GGW2XY6IHJ/graph.json","events_json":"https://pith.science/api/pith-number/JRZRKXK24H67FRR2GGW2XY6IHJ/events.json","paper":"https://pith.science/paper/JRZRKXK2"},"agent_actions":{"view_html":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ","download_json":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ.json","view_paper":"https://pith.science/paper/JRZRKXK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03858&json=true","fetch_graph":"https://pith.science/api/pith-number/JRZRKXK24H67FRR2GGW2XY6IHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JRZRKXK24H67FRR2GGW2XY6IHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ/action/storage_attestation","attest_author":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ/action/author_attestation","sign_citation":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ/action/citation_signature","submit_replication":"https://pith.science/pith/JRZRKXK24H67FRR2GGW2XY6IHJ/action/replication_record"}},"created_at":"2026-07-05T03:13:06.119086+00:00","updated_at":"2026-07-05T03:13:06.119086+00:00"}