{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:REUU3XFM3SHH3DCHA42UEURQFV","short_pith_number":"pith:REUU3XFM","schema_version":"1.0","canonical_sha256":"89294ddcacdc8e7d8c4707354252302d504172127d14eee564ab580bc5a9ce51","source":{"kind":"arxiv","id":"1908.08025","version":3},"attestation_state":"computed","paper":{"title":"WikiCREM: A Large Unsupervised Corpus for Coreference Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana-Maria Cretu, Oana-Maria Camburu, Phil Blunsom, Thomas Lukasiewicz, Vid Kocijan, Yordan Yordanov","submitted_at":"2019-08-21T17:42:03Z","abstract_excerpt":"Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datas"},"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":"1908.08025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T17:42:03Z","cross_cats_sorted":[],"title_canon_sha256":"4b9efd33ec952c0937c6c5c68147516bdc59c21404b2d422a57b1b4b1ccdd7e3","abstract_canon_sha256":"96f5fa44952f9713d6404158aa7d102208823d44376cc0caf01eb0fca4fa45c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:35.905992Z","signature_b64":"VO6LcnmFD59uQIOB2ZiOTKehbJYyIelui8QhDdsx+nuzhHmOVxClwa698W2kg9dPVw3CzJ/8g4K0NT4e40biDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89294ddcacdc8e7d8c4707354252302d504172127d14eee564ab580bc5a9ce51","last_reissued_at":"2026-07-05T00:11:35.905598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:35.905598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiCREM: A Large Unsupervised Corpus for Coreference Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana-Maria Cretu, Oana-Maria Camburu, Phil Blunsom, Thomas Lukasiewicz, Vid Kocijan, Yordan Yordanov","submitted_at":"2019-08-21T17:42:03Z","abstract_excerpt":"Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08025","kind":"arxiv","version":3},"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/1908.08025/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":"1908.08025","created_at":"2026-07-05T00:11:35.905652+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08025v3","created_at":"2026-07-05T00:11:35.905652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08025","created_at":"2026-07-05T00:11:35.905652+00:00"},{"alias_kind":"pith_short_12","alias_value":"REUU3XFM3SHH","created_at":"2026-07-05T00:11:35.905652+00:00"},{"alias_kind":"pith_short_16","alias_value":"REUU3XFM3SHH3DCH","created_at":"2026-07-05T00:11:35.905652+00:00"},{"alias_kind":"pith_short_8","alias_value":"REUU3XFM","created_at":"2026-07-05T00:11:35.905652+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/REUU3XFM3SHH3DCHA42UEURQFV","json":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV.json","graph_json":"https://pith.science/api/pith-number/REUU3XFM3SHH3DCHA42UEURQFV/graph.json","events_json":"https://pith.science/api/pith-number/REUU3XFM3SHH3DCHA42UEURQFV/events.json","paper":"https://pith.science/paper/REUU3XFM"},"agent_actions":{"view_html":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV","download_json":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV.json","view_paper":"https://pith.science/paper/REUU3XFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08025&json=true","fetch_graph":"https://pith.science/api/pith-number/REUU3XFM3SHH3DCHA42UEURQFV/graph.json","fetch_events":"https://pith.science/api/pith-number/REUU3XFM3SHH3DCHA42UEURQFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV/action/storage_attestation","attest_author":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV/action/author_attestation","sign_citation":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV/action/citation_signature","submit_replication":"https://pith.science/pith/REUU3XFM3SHH3DCHA42UEURQFV/action/replication_record"}},"created_at":"2026-07-05T00:11:35.905652+00:00","updated_at":"2026-07-05T00:11:35.905652+00:00"}