{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:CEVZMGLWNSBFUMWHYAPQADOA6Z","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":"d852ae99f47b0e32b189def9a7475c68f6ec37afec1111cb01f87eed4186715d","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-01T02:49:08Z","title_canon_sha256":"d6daa8b9db4d1a1fcf08b52eebfc5f624ef97f7919bb1b945fef07da2f28f7d7"},"schema_version":"1.0","source":{"id":"1307.0261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.0261","created_at":"2026-05-18T03:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"1307.0261v1","created_at":"2026-05-18T03:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.0261","created_at":"2026-05-18T03:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"CEVZMGLWNSBF","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"CEVZMGLWNSBFUMWH","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"CEVZMGLW","created_at":"2026-05-18T12:27:40Z"}],"graph_snapshots":[{"event_id":"sha256:4bc8af01a85b341e9217090651774f76a3f9d1ebfd5b19fd8e9aba1c619767f0","target":"graph","created_at":"2026-05-18T03:19:33Z","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"},"paper":{"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","authors_text":"Bhavana Dalvi, Jamie Callan, William W. Cohen","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-01T02:49:08Z","title":"WebSets: Extracting Sets of Entities from the Web Using Unsupervised Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.0261","kind":"arxiv","version":1},"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":"sha256:0cd7391e658fe49306844fea21616482740b012d29854a79a8b4f218a821b972","target":"record","created_at":"2026-05-18T03:19:33Z","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":"d852ae99f47b0e32b189def9a7475c68f6ec37afec1111cb01f87eed4186715d","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-01T02:49:08Z","title_canon_sha256":"d6daa8b9db4d1a1fcf08b52eebfc5f624ef97f7919bb1b945fef07da2f28f7d7"},"schema_version":"1.0","source":{"id":"1307.0261","kind":"arxiv","version":1}},"canonical_sha256":"112b9619766c825a32c7c01f000dc0f64503bbc7c85a57b31166cd721ad6b3df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"112b9619766c825a32c7c01f000dc0f64503bbc7c85a57b31166cd721ad6b3df","first_computed_at":"2026-05-18T03:19:33.843349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:19:33.843349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YuWQh8+wKoyH9B8R1lHv/AMhq1XcsuKzd0iwFn+L7+hyXa/yek3e2MW0df2KrSwLr9vm2TcS3ecQoXEiiBxBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:19:33.843931Z","signed_message":"canonical_sha256_bytes"},"source_id":"1307.0261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd7391e658fe49306844fea21616482740b012d29854a79a8b4f218a821b972","sha256:4bc8af01a85b341e9217090651774f76a3f9d1ebfd5b19fd8e9aba1c619767f0"],"state_sha256":"374f62bfecd003da8c552bc113098c8c8ad47f22e83260c9cd6c64619eee4fb4"}