{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:REUU3XFM3SHH3DCHA42UEURQFV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"96f5fa44952f9713d6404158aa7d102208823d44376cc0caf01eb0fca4fa45c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T17:42:03Z","title_canon_sha256":"4b9efd33ec952c0937c6c5c68147516bdc59c21404b2d422a57b1b4b1ccdd7e3"},"schema_version":"1.0","source":{"id":"1908.08025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08025","created_at":"2026-07-05T00:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08025v3","created_at":"2026-07-05T00:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08025","created_at":"2026-07-05T00:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"REUU3XFM3SHH","created_at":"2026-07-05T00:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"REUU3XFM3SHH3DCH","created_at":"2026-07-05T00:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"REUU3XFM","created_at":"2026-07-05T00:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:018694980c3acd2ea8e23cddfc76e3c6c835db13c3e41ee604651c2f33918c09","target":"graph","created_at":"2026-07-05T00:11:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ana-Maria Cretu, Oana-Maria Camburu, Phil Blunsom, Thomas Lukasiewicz, Vid Kocijan, Yordan Yordanov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T17:42:03Z","title":"WikiCREM: A Large Unsupervised Corpus for Coreference Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08025","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f77a81eb0ffff2058842e8bd334aae9f47b1f96573bd20cff79f1d8ead90ddad","target":"record","created_at":"2026-07-05T00:11:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"96f5fa44952f9713d6404158aa7d102208823d44376cc0caf01eb0fca4fa45c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T17:42:03Z","title_canon_sha256":"4b9efd33ec952c0937c6c5c68147516bdc59c21404b2d422a57b1b4b1ccdd7e3"},"schema_version":"1.0","source":{"id":"1908.08025","kind":"arxiv","version":3}},"canonical_sha256":"89294ddcacdc8e7d8c4707354252302d504172127d14eee564ab580bc5a9ce51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89294ddcacdc8e7d8c4707354252302d504172127d14eee564ab580bc5a9ce51","first_computed_at":"2026-07-05T00:11:35.905598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:35.905598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VO6LcnmFD59uQIOB2ZiOTKehbJYyIelui8QhDdsx+nuzhHmOVxClwa698W2kg9dPVw3CzJ/8g4K0NT4e40biDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:35.905992Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f77a81eb0ffff2058842e8bd334aae9f47b1f96573bd20cff79f1d8ead90ddad","sha256:018694980c3acd2ea8e23cddfc76e3c6c835db13c3e41ee604651c2f33918c09"],"state_sha256":"6fa436a57cbf47e3ee832cdc463474ba3bd1952e9045e815709328a8d06bc588"}