{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:C6LDHU7MLA6LWV7HSDZSNNPISP","short_pith_number":"pith:C6LDHU7M","schema_version":"1.0","canonical_sha256":"179633d3ec583cbb57e790f326b5e893e9ab4ab14fb97d68597976d7ee876df9","source":{"kind":"arxiv","id":"1311.3987","version":1},"attestation_state":"computed","paper":{"title":"Big Data and Cross-Document Coreference Resolution: Current State and Future Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IR"],"primary_cat":"cs.CL","authors_text":"Boualem Benatallah, Seung Hwan Ryu, Seyed-Mehdi-Reza Beheshti, Srikumar Venugopal, Wei Wang","submitted_at":"2013-11-14T06:10:15Z","abstract_excerpt":"Information Extraction (IE) is the task of automatically extracting structured information from unstructured/semi-structured machine-readable documents. Among various IE tasks, extracting actionable intelligence from ever-increasing amount of data depends critically upon Cross-Document Coreference Resolution (CDCR) - the task of identifying entity mentions across multiple documents that refer to the same underlying entity. Recently, document datasets of the order of peta-/tera-bytes has raised many challenges for performing effective CDCR such as scaling to large numbers of mentions and limite"},"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":"1311.3987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-11-14T06:10:15Z","cross_cats_sorted":["cs.DC","cs.IR"],"title_canon_sha256":"33a985f8dbd404294c2ba3d915a2d9441dba1756852056e86f9e51b4cdcf3763","abstract_canon_sha256":"45d9352016be8c9e966fc7300c903af933f5776b32e117a708f89b5431d5f1c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:06:54.015408Z","signature_b64":"nFV/eAmgbgfvcpGeMdqeDwbu+ginhPqVC+MkCWmJeXH8G/a9/Hu78ndnJNvsjDGsDo0zjV+Buyx0EuEMHAOuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"179633d3ec583cbb57e790f326b5e893e9ab4ab14fb97d68597976d7ee876df9","last_reissued_at":"2026-05-18T03:06:54.014719Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:06:54.014719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Big Data and Cross-Document Coreference Resolution: Current State and Future Opportunities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IR"],"primary_cat":"cs.CL","authors_text":"Boualem Benatallah, Seung Hwan Ryu, Seyed-Mehdi-Reza Beheshti, Srikumar Venugopal, Wei Wang","submitted_at":"2013-11-14T06:10:15Z","abstract_excerpt":"Information Extraction (IE) is the task of automatically extracting structured information from unstructured/semi-structured machine-readable documents. Among various IE tasks, extracting actionable intelligence from ever-increasing amount of data depends critically upon Cross-Document Coreference Resolution (CDCR) - the task of identifying entity mentions across multiple documents that refer to the same underlying entity. Recently, document datasets of the order of peta-/tera-bytes has raised many challenges for performing effective CDCR such as scaling to large numbers of mentions and limite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.3987","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":"1311.3987","created_at":"2026-05-18T03:06:54.014830+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.3987v1","created_at":"2026-05-18T03:06:54.014830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.3987","created_at":"2026-05-18T03:06:54.014830+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6LDHU7MLA6L","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6LDHU7MLA6LWV7H","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6LDHU7M","created_at":"2026-05-18T12:27:40.988391+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/C6LDHU7MLA6LWV7HSDZSNNPISP","json":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP.json","graph_json":"https://pith.science/api/pith-number/C6LDHU7MLA6LWV7HSDZSNNPISP/graph.json","events_json":"https://pith.science/api/pith-number/C6LDHU7MLA6LWV7HSDZSNNPISP/events.json","paper":"https://pith.science/paper/C6LDHU7M"},"agent_actions":{"view_html":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP","download_json":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP.json","view_paper":"https://pith.science/paper/C6LDHU7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.3987&json=true","fetch_graph":"https://pith.science/api/pith-number/C6LDHU7MLA6LWV7HSDZSNNPISP/graph.json","fetch_events":"https://pith.science/api/pith-number/C6LDHU7MLA6LWV7HSDZSNNPISP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP/action/storage_attestation","attest_author":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP/action/author_attestation","sign_citation":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP/action/citation_signature","submit_replication":"https://pith.science/pith/C6LDHU7MLA6LWV7HSDZSNNPISP/action/replication_record"}},"created_at":"2026-05-18T03:06:54.014830+00:00","updated_at":"2026-05-18T03:06:54.014830+00:00"}