{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOC4QV7GAX4O2G77YT5SR2NSRD","short_pith_number":"pith:OOC4QV7G","schema_version":"1.0","canonical_sha256":"7385c857e605f8ed1bffc4fb28e9b288eb7ad45291968082320fd4c11bfa3a20","source":{"kind":"arxiv","id":"2406.15576","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Entity Coreference and Disambiguation for Historical Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Abhishek Arora, Emily Silcock, Leander Heldring, Melissa Dell","submitted_at":"2024-06-21T18:22:14Z","abstract_excerpt":"Massive-scale historical document collections are crucial for social science research. Despite increasing digitization, these documents typically lack unique cross-document identifiers for individuals mentioned within the texts, as well as individual identifiers from external knowledgebases like Wikipedia/Wikidata. Existing entity disambiguation methods often fall short in accuracy for historical documents, which are replete with individuals not remembered in contemporary knowledgebases. This study makes three key contributions to improve cross-document coreference resolution and disambiguatio"},"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":"2406.15576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T18:22:14Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"52958f7be4c12fb9fe9f2863ceda076fed164ef4c74c0c45f2761a8aa4cb68f6","abstract_canon_sha256":"3863748cb060beeae5b87b65c543624a66947e0dcdc2b7e145e74f366d04bc41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:24.702861Z","signature_b64":"ElrPluL8Fdy1+DxknIJZEwIA8b89JpAK8xHRWjK27dYqqRCOxFw6bVLxfDMxJmVmoZJQzwWyBIyPPIzR/53xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7385c857e605f8ed1bffc4fb28e9b288eb7ad45291968082320fd4c11bfa3a20","last_reissued_at":"2026-07-05T08:35:24.702434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:24.702434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Entity Coreference and Disambiguation for Historical Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Abhishek Arora, Emily Silcock, Leander Heldring, Melissa Dell","submitted_at":"2024-06-21T18:22:14Z","abstract_excerpt":"Massive-scale historical document collections are crucial for social science research. Despite increasing digitization, these documents typically lack unique cross-document identifiers for individuals mentioned within the texts, as well as individual identifiers from external knowledgebases like Wikipedia/Wikidata. Existing entity disambiguation methods often fall short in accuracy for historical documents, which are replete with individuals not remembered in contemporary knowledgebases. This study makes three key contributions to improve cross-document coreference resolution and disambiguatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15576","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/2406.15576/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":"2406.15576","created_at":"2026-07-05T08:35:24.702490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15576v1","created_at":"2026-07-05T08:35:24.702490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15576","created_at":"2026-07-05T08:35:24.702490+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOC4QV7GAX4O","created_at":"2026-07-05T08:35:24.702490+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOC4QV7GAX4O2G77","created_at":"2026-07-05T08:35:24.702490+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOC4QV7G","created_at":"2026-07-05T08:35:24.702490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD","json":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD.json","graph_json":"https://pith.science/api/pith-number/OOC4QV7GAX4O2G77YT5SR2NSRD/graph.json","events_json":"https://pith.science/api/pith-number/OOC4QV7GAX4O2G77YT5SR2NSRD/events.json","paper":"https://pith.science/paper/OOC4QV7G"},"agent_actions":{"view_html":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD","download_json":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD.json","view_paper":"https://pith.science/paper/OOC4QV7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15576&json=true","fetch_graph":"https://pith.science/api/pith-number/OOC4QV7GAX4O2G77YT5SR2NSRD/graph.json","fetch_events":"https://pith.science/api/pith-number/OOC4QV7GAX4O2G77YT5SR2NSRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD/action/storage_attestation","attest_author":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD/action/author_attestation","sign_citation":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD/action/citation_signature","submit_replication":"https://pith.science/pith/OOC4QV7GAX4O2G77YT5SR2NSRD/action/replication_record"}},"created_at":"2026-07-05T08:35:24.702490+00:00","updated_at":"2026-07-05T08:35:24.702490+00:00"}