{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SH3L4D6PKDCYDVZXISQKUQBYPI","short_pith_number":"pith:SH3L4D6P","schema_version":"1.0","canonical_sha256":"91f6be0fcf50c581d73744a0aa40387a24c340559bd0bbb651966a78e96488eb","source":{"kind":"arxiv","id":"1804.09301","version":1},"attestation_state":"computed","paper":{"title":"Gender Bias in Coreference Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Brian Leonard, Jason Naradowsky, Rachel Rudinger","submitted_at":"2018-04-25T00:46:14Z","abstract_excerpt":"We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these \"Winogender schemas,\" we evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems, and correlate this bias with real-world and textual gender statistics."},"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":"1804.09301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-25T00:46:14Z","cross_cats_sorted":[],"title_canon_sha256":"d5a5d73994f5b9b4be29b87baa2aa88f1b3658fd0a0df4caa91035532b468856","abstract_canon_sha256":"5f3556b25dcfc823c1025720b0d5f118d6784fedd3d6fd3b461b2b8285fb5e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:32.187850Z","signature_b64":"g+0EolY5j1jA+5l7s6l81FIj/kSZa7UsoS3qvMpeKkyNS9uKPdyaBkl7NxohAjkO13tvHby/u5RLJMDZghuYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f6be0fcf50c581d73744a0aa40387a24c340559bd0bbb651966a78e96488eb","last_reissued_at":"2026-05-18T00:17:32.187131Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:32.187131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gender Bias in Coreference Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Brian Leonard, Jason Naradowsky, Rachel Rudinger","submitted_at":"2018-04-25T00:46:14Z","abstract_excerpt":"We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these \"Winogender schemas,\" we evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems, and correlate this bias with real-world and textual gender statistics."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09301","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":"1804.09301","created_at":"2026-05-18T00:17:32.187237+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09301v1","created_at":"2026-05-18T00:17:32.187237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09301","created_at":"2026-05-18T00:17:32.187237+00:00"},{"alias_kind":"pith_short_12","alias_value":"SH3L4D6PKDCY","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SH3L4D6PKDCYDVZX","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SH3L4D6P","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":260,"is_internal_anchor":true},{"citing_arxiv_id":"2201.10005","citing_title":"Text and Code Embeddings by Contrastive Pre-Training","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12946","citing_title":"Parcae: Scaling Laws For Stable Looped Language Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI","json":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI.json","graph_json":"https://pith.science/api/pith-number/SH3L4D6PKDCYDVZXISQKUQBYPI/graph.json","events_json":"https://pith.science/api/pith-number/SH3L4D6PKDCYDVZXISQKUQBYPI/events.json","paper":"https://pith.science/paper/SH3L4D6P"},"agent_actions":{"view_html":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI","download_json":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI.json","view_paper":"https://pith.science/paper/SH3L4D6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09301&json=true","fetch_graph":"https://pith.science/api/pith-number/SH3L4D6PKDCYDVZXISQKUQBYPI/graph.json","fetch_events":"https://pith.science/api/pith-number/SH3L4D6PKDCYDVZXISQKUQBYPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI/action/storage_attestation","attest_author":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI/action/author_attestation","sign_citation":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI/action/citation_signature","submit_replication":"https://pith.science/pith/SH3L4D6PKDCYDVZXISQKUQBYPI/action/replication_record"}},"created_at":"2026-05-18T00:17:32.187237+00:00","updated_at":"2026-05-18T00:17:32.187237+00:00"}