{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LMV4RQNPZ7TORA2CT4OOJCKJEL","short_pith_number":"pith:LMV4RQNP","schema_version":"1.0","canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","source":{"kind":"arxiv","id":"1906.01250","version":1},"attestation_state":"computed","paper":{"title":"Boosting Entity Linking Performance by Leveraging Unlabeled Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ivan Titov, Phong Le","submitted_at":"2019-06-04T07:49:46Z","abstract_excerpt":"Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts"},"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":"1906.01250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T07:49:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c53afa478f74203c2e0b356ffb7334b9fdc88a86acb54128f7be46bd4262ea1","abstract_canon_sha256":"5469aab2af879c4e9e8a08d2aaa075bae867698eb04a881c36e6fdb0ab8af36c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:17.340459Z","signature_b64":"8TxauihxE5RQz89jFbOBos5pCyJQa1H5l2YhMeULaJUve0viO/W1wkEZXcv+FhDLiqqf5KGB+FxAiHQPryrQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2bc8c1afcfe6e883429f1ce4894922e1dd809354c5e5f0e24adf00e8078941","last_reissued_at":"2026-05-17T23:44:17.339843Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:17.339843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Entity Linking Performance by Leveraging Unlabeled Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ivan Titov, Phong Le","submitted_at":"2019-06-04T07:49:46Z","abstract_excerpt":"Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01250","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":"1906.01250","created_at":"2026-05-17T23:44:17.339933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01250v1","created_at":"2026-05-17T23:44:17.339933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01250","created_at":"2026-05-17T23:44:17.339933+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMV4RQNPZ7TO","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMV4RQNPZ7TORA2C","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMV4RQNP","created_at":"2026-05-18T12:33:21.387695+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/LMV4RQNPZ7TORA2CT4OOJCKJEL","json":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL.json","graph_json":"https://pith.science/api/pith-number/LMV4RQNPZ7TORA2CT4OOJCKJEL/graph.json","events_json":"https://pith.science/api/pith-number/LMV4RQNPZ7TORA2CT4OOJCKJEL/events.json","paper":"https://pith.science/paper/LMV4RQNP"},"agent_actions":{"view_html":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL","download_json":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL.json","view_paper":"https://pith.science/paper/LMV4RQNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01250&json=true","fetch_graph":"https://pith.science/api/pith-number/LMV4RQNPZ7TORA2CT4OOJCKJEL/graph.json","fetch_events":"https://pith.science/api/pith-number/LMV4RQNPZ7TORA2CT4OOJCKJEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/action/storage_attestation","attest_author":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/action/author_attestation","sign_citation":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/action/citation_signature","submit_replication":"https://pith.science/pith/LMV4RQNPZ7TORA2CT4OOJCKJEL/action/replication_record"}},"created_at":"2026-05-17T23:44:17.339933+00:00","updated_at":"2026-05-17T23:44:17.339933+00:00"}