{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q5YPIXN2DGSCYZSHO5WAHR2IMP","short_pith_number":"pith:Q5YPIXN2","schema_version":"1.0","canonical_sha256":"8770f45dba19a42c6647776c03c74863ec3217e12767e3a10c589e8de6f36038","source":{"kind":"arxiv","id":"2204.05879","version":1},"attestation_state":"computed","paper":{"title":"Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, Claire Gardent","submitted_at":"2022-04-12T15:16:57Z","abstract_excerpt":"Generating factual, long-form text such as Wikipedia articles raises three key challenges: how to gather relevant evidence, how to structure information into well-formed text, and how to ensure that the generated text is factually correct. We address these by developing a model for English text that uses a retrieval mechanism to identify relevant supporting information on the web and a cache-based pre-trained encoder-decoder to generate long-form biographies section by section, including citation information. To assess the impact of available web evidence on the output text, we compare the per"},"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":"2204.05879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-12T15:16:57Z","cross_cats_sorted":[],"title_canon_sha256":"90e65e29aecc6623fccd34ae193b859c1f52319cda726efd1ef8cbd4da0586c7","abstract_canon_sha256":"f9ebc8931d5d14e10e41c6b7a3dae553594b353f9f4d5d88447399880683364a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:03.432836Z","signature_b64":"sGfgTjm4fmIQn+70D1YSvM8qkM4f1VydXLkda+en2TWI0xWPIwQfPtbsN9lrElk5qJ4ynbesNTsPXuxDtdL+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8770f45dba19a42c6647776c03c74863ec3217e12767e3a10c589e8de6f36038","last_reissued_at":"2026-07-05T04:14:03.432364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:03.432364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angela Fan, Claire Gardent","submitted_at":"2022-04-12T15:16:57Z","abstract_excerpt":"Generating factual, long-form text such as Wikipedia articles raises three key challenges: how to gather relevant evidence, how to structure information into well-formed text, and how to ensure that the generated text is factually correct. We address these by developing a model for English text that uses a retrieval mechanism to identify relevant supporting information on the web and a cache-based pre-trained encoder-decoder to generate long-form biographies section by section, including citation information. To assess the impact of available web evidence on the output text, we compare the per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05879","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.05879/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":"2204.05879","created_at":"2026-07-05T04:14:03.432427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05879v1","created_at":"2026-07-05T04:14:03.432427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05879","created_at":"2026-07-05T04:14:03.432427+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5YPIXN2DGSC","created_at":"2026-07-05T04:14:03.432427+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5YPIXN2DGSCYZSH","created_at":"2026-07-05T04:14:03.432427+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5YPIXN2","created_at":"2026-07-05T04:14:03.432427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12088","citing_title":"Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP","json":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP.json","graph_json":"https://pith.science/api/pith-number/Q5YPIXN2DGSCYZSHO5WAHR2IMP/graph.json","events_json":"https://pith.science/api/pith-number/Q5YPIXN2DGSCYZSHO5WAHR2IMP/events.json","paper":"https://pith.science/paper/Q5YPIXN2"},"agent_actions":{"view_html":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP","download_json":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP.json","view_paper":"https://pith.science/paper/Q5YPIXN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05879&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5YPIXN2DGSCYZSHO5WAHR2IMP/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5YPIXN2DGSCYZSHO5WAHR2IMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP/action/storage_attestation","attest_author":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP/action/author_attestation","sign_citation":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP/action/citation_signature","submit_replication":"https://pith.science/pith/Q5YPIXN2DGSCYZSHO5WAHR2IMP/action/replication_record"}},"created_at":"2026-07-05T04:14:03.432427+00:00","updated_at":"2026-07-05T04:14:03.432427+00:00"}