{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:CEVZMGLWNSBFUMWHYAPQADOA6Z","short_pith_number":"pith:CEVZMGLW","schema_version":"1.0","canonical_sha256":"112b9619766c825a32c7c01f000dc0f64503bbc7c85a57b31166cd721ad6b3df","source":{"kind":"arxiv","id":"1307.0261","version":1},"attestation_state":"computed","paper":{"title":"WebSets: Extracting Sets of Entities from the Web Using Unsupervised Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Bhavana Dalvi, Jamie Callan, William W. Cohen","submitted_at":"2013-07-01T02:49:08Z","abstract_excerpt":"We describe a open-domain information extraction method for extracting concept-instance pairs from an HTML corpus. Most earlier approaches to this problem rely on combining clusters of distributionally similar terms and concept-instance pairs obtained with Hearst patterns. In contrast, our method relies on a novel approach for clustering terms found in HTML tables, and then assigning concept names to these clusters using Hearst patterns. The method can be efficiently applied to a large corpus, and experimental results on several datasets show that our method can accurately extract large number"},"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":"1307.0261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-01T02:49:08Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"d6daa8b9db4d1a1fcf08b52eebfc5f624ef97f7919bb1b945fef07da2f28f7d7","abstract_canon_sha256":"d852ae99f47b0e32b189def9a7475c68f6ec37afec1111cb01f87eed4186715d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:19:33.843931Z","signature_b64":"8YuWQh8+wKoyH9B8R1lHv/AMhq1XcsuKzd0iwFn+L7+hyXa/yek3e2MW0df2KrSwLr9vm2TcS3ecQoXEiiBxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"112b9619766c825a32c7c01f000dc0f64503bbc7c85a57b31166cd721ad6b3df","last_reissued_at":"2026-05-18T03:19:33.843349Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:19:33.843349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebSets: Extracting Sets of Entities from the Web Using Unsupervised Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Bhavana Dalvi, Jamie Callan, William W. Cohen","submitted_at":"2013-07-01T02:49:08Z","abstract_excerpt":"We describe a open-domain information extraction method for extracting concept-instance pairs from an HTML corpus. Most earlier approaches to this problem rely on combining clusters of distributionally similar terms and concept-instance pairs obtained with Hearst patterns. In contrast, our method relies on a novel approach for clustering terms found in HTML tables, and then assigning concept names to these clusters using Hearst patterns. The method can be efficiently applied to a large corpus, and experimental results on several datasets show that our method can accurately extract large number"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.0261","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":"1307.0261","created_at":"2026-05-18T03:19:33.843434+00:00"},{"alias_kind":"arxiv_version","alias_value":"1307.0261v1","created_at":"2026-05-18T03:19:33.843434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.0261","created_at":"2026-05-18T03:19:33.843434+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEVZMGLWNSBF","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEVZMGLWNSBFUMWH","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEVZMGLW","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/CEVZMGLWNSBFUMWHYAPQADOA6Z","json":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z.json","graph_json":"https://pith.science/api/pith-number/CEVZMGLWNSBFUMWHYAPQADOA6Z/graph.json","events_json":"https://pith.science/api/pith-number/CEVZMGLWNSBFUMWHYAPQADOA6Z/events.json","paper":"https://pith.science/paper/CEVZMGLW"},"agent_actions":{"view_html":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z","download_json":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z.json","view_paper":"https://pith.science/paper/CEVZMGLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1307.0261&json=true","fetch_graph":"https://pith.science/api/pith-number/CEVZMGLWNSBFUMWHYAPQADOA6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CEVZMGLWNSBFUMWHYAPQADOA6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z/action/storage_attestation","attest_author":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z/action/author_attestation","sign_citation":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z/action/citation_signature","submit_replication":"https://pith.science/pith/CEVZMGLWNSBFUMWHYAPQADOA6Z/action/replication_record"}},"created_at":"2026-05-18T03:19:33.843434+00:00","updated_at":"2026-05-18T03:19:33.843434+00:00"}