{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:6JVYWQ2T3ESJXP7KOEQBL35SWK","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":"d883ff37e4cba7e8be4ec67806b4fa867e2577418707c73c75a37dd44b9caeee","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2011-04-14T16:27:35Z","title_canon_sha256":"3ebe1d3d301ce0aeac3a4353141df05e93e0b8d910dc0bcb81b3d70f215b76bf"},"schema_version":"1.0","source":{"id":"1104.2824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1104.2824","created_at":"2026-05-18T02:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"1104.2824v1","created_at":"2026-05-18T02:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1104.2824","created_at":"2026-05-18T02:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"6JVYWQ2T3ESJ","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"6JVYWQ2T3ESJXP7K","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"6JVYWQ2T","created_at":"2026-05-18T12:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:c975956cd04b2a6d806cbce2f0a2c7bae2d944dd2c4f5311d8a264f54087de70","target":"graph","created_at":"2026-05-18T02:22:09Z","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":"Many websites with an underlying database containing structured data provide the richest and most dense source of information relevant for topical data integration. The real data integration requires sustainable and reliable pattern discovery to enable accurate content retrieval and to recognize pattern changes from time to time; yet, extracting the structured data from web documents is still lacking from its accuracy. This paper proposes the bar-tree representation to describe the whole pattern of web pages in an efficient way based on the reverse algorithm. While previous algorithms always t","authors_text":"L.T. Handoko, Z. Akbar","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2011-04-14T16:27:35Z","title":"Pattern discovery for semi-structured web pages using bar-tree representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1104.2824","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":"sha256:9f0dc71221e4bc1fbd1c5fffb213a435a0a34fbc1cbcf285e882370a05280246","target":"record","created_at":"2026-05-18T02:22:09Z","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":"d883ff37e4cba7e8be4ec67806b4fa867e2577418707c73c75a37dd44b9caeee","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2011-04-14T16:27:35Z","title_canon_sha256":"3ebe1d3d301ce0aeac3a4353141df05e93e0b8d910dc0bcb81b3d70f215b76bf"},"schema_version":"1.0","source":{"id":"1104.2824","kind":"arxiv","version":1}},"canonical_sha256":"f26b8b4353d9249bbfea712015efb2b2aba53905ce8d023856da10d9aeff6321","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f26b8b4353d9249bbfea712015efb2b2aba53905ce8d023856da10d9aeff6321","first_computed_at":"2026-05-18T02:22:09.167694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:22:09.167694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNbM4JvpQhDu/R4tGUu48udQPDeASSFRrNT0tDqbcy6HpNg0aB3+K37Vw2cibe6FwS1S8dryjFemaZ53HP3tCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:22:09.168264Z","signed_message":"canonical_sha256_bytes"},"source_id":"1104.2824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f0dc71221e4bc1fbd1c5fffb213a435a0a34fbc1cbcf285e882370a05280246","sha256:c975956cd04b2a6d806cbce2f0a2c7bae2d944dd2c4f5311d8a264f54087de70"],"state_sha256":"a5189c917d6d4532d0cb4af055efd1653f7bb218cd13989233d26e796b763d1b"}