{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MFOO6TC3TDC52J6WVH7QHZII7W","short_pith_number":"pith:MFOO6TC3","schema_version":"1.0","canonical_sha256":"615cef4c5b98c5dd27d6a9ff03e508fdb8f81f32191e15adf56004a98e5d8191","source":{"kind":"arxiv","id":"1703.04498","version":1},"attestation_state":"computed","paper":{"title":"High-Throughput and Language-Agnostic Entity Disambiguation and Linking on User Generated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Guoning Hu, Nemanja Spasojevic, Preeti Bhargava","submitted_at":"2017-03-13T17:34:18Z","abstract_excerpt":"The Entity Disambiguation and Linking (EDL) task matches entity mentions in text to a unique Knowledge Base (KB) identifier such as a Wikipedia or Freebase id. It plays a critical role in the construction of a high quality information network, and can be further leveraged for a variety of information retrieval and NLP tasks such as text categorization and document tagging. EDL is a complex and challenging problem due to ambiguity of the mentions and real world text being multi-lingual. Moreover, EDL systems need to have high throughput and should be lightweight in order to scale to large 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":"1703.04498","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-13T17:34:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fa2c3bbad7465ca9dd31e5483fa2ae95f07bd27aff78f919bea860218e0e4625","abstract_canon_sha256":"6a7740864a15bbf1851d69909a222791967de0f427916ef7d35d88dc7b43574e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:48.444013Z","signature_b64":"FilOISCVdPaMg+2HZqAPEtwxNjivKKyTfchVOWdIyxJmLoeM7WAvYmC/hrCXkyy9MV6JtpFuqjGv3tRed/llDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"615cef4c5b98c5dd27d6a9ff03e508fdb8f81f32191e15adf56004a98e5d8191","last_reissued_at":"2026-05-18T00:48:48.443209Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:48.443209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Throughput and Language-Agnostic Entity Disambiguation and Linking on User Generated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Guoning Hu, Nemanja Spasojevic, Preeti Bhargava","submitted_at":"2017-03-13T17:34:18Z","abstract_excerpt":"The Entity Disambiguation and Linking (EDL) task matches entity mentions in text to a unique Knowledge Base (KB) identifier such as a Wikipedia or Freebase id. It plays a critical role in the construction of a high quality information network, and can be further leveraged for a variety of information retrieval and NLP tasks such as text categorization and document tagging. EDL is a complex and challenging problem due to ambiguity of the mentions and real world text being multi-lingual. Moreover, EDL systems need to have high throughput and should be lightweight in order to scale to large datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04498","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":"1703.04498","created_at":"2026-05-18T00:48:48.443361+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04498v1","created_at":"2026-05-18T00:48:48.443361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04498","created_at":"2026-05-18T00:48:48.443361+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFOO6TC3TDC5","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFOO6TC3TDC52J6W","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFOO6TC3","created_at":"2026-05-18T12:31:31.346846+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/MFOO6TC3TDC52J6WVH7QHZII7W","json":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W.json","graph_json":"https://pith.science/api/pith-number/MFOO6TC3TDC52J6WVH7QHZII7W/graph.json","events_json":"https://pith.science/api/pith-number/MFOO6TC3TDC52J6WVH7QHZII7W/events.json","paper":"https://pith.science/paper/MFOO6TC3"},"agent_actions":{"view_html":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W","download_json":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W.json","view_paper":"https://pith.science/paper/MFOO6TC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04498&json=true","fetch_graph":"https://pith.science/api/pith-number/MFOO6TC3TDC52J6WVH7QHZII7W/graph.json","fetch_events":"https://pith.science/api/pith-number/MFOO6TC3TDC52J6WVH7QHZII7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W/action/storage_attestation","attest_author":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W/action/author_attestation","sign_citation":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W/action/citation_signature","submit_replication":"https://pith.science/pith/MFOO6TC3TDC52J6WVH7QHZII7W/action/replication_record"}},"created_at":"2026-05-18T00:48:48.443361+00:00","updated_at":"2026-05-18T00:48:48.443361+00:00"}