{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4XL3SPWCB6QAL2475QDVOWYO6M","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":"c0b03b62071b3a0cf22cafb521d6d32ec3356d443da98b06b4c3d46f409d1de8","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T15:05:00Z","title_canon_sha256":"40cb260e23c53eb21ad0d1debb51f4669bab49657412a16fcaf351dce3e22095"},"schema_version":"1.0","source":{"id":"2502.14625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14625","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14625v1","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14625","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"4XL3SPWCB6QA","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"4XL3SPWCB6QAL247","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"4XL3SPWC","created_at":"2026-07-05T10:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:567581827883d2dd930e988ec7e74b3526c4fbf403f3949c8200476c6383a70f","target":"graph","created_at":"2026-07-05T10:17:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.14625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focused on the problem of extracting information from web pages containing many records, a task of growing importance in the era of massive web data. Recently, the development of neural network methods has improved the quality of information extraction from web pages. Nevertheless, most of the research and datasets are aimed at studying detailed pages. This has left multi-record \"list pages\" relatively understudied, despite their widespread presence and practical significance.\n  To address this gap, we created a large-scale, open-access dataset specifically designed for list ","authors_text":"Alexander Kustenkov, Alexander Yatskov, Maksim Varlamov","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T15:05:00Z","title":"Multi-Record Web Page Information Extraction From News Websites"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14625","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:d50c590cfd69999f6deeb4fd23052ef1ffd818171d196977df87619926abcad2","target":"record","created_at":"2026-07-05T10:17:30Z","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":"c0b03b62071b3a0cf22cafb521d6d32ec3356d443da98b06b4c3d46f409d1de8","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T15:05:00Z","title_canon_sha256":"40cb260e23c53eb21ad0d1debb51f4669bab49657412a16fcaf351dce3e22095"},"schema_version":"1.0","source":{"id":"2502.14625","kind":"arxiv","version":1}},"canonical_sha256":"e5d7b93ec20fa005eb9fec07575b0ef315007b92010949f2e31d9b7e3d91bf7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5d7b93ec20fa005eb9fec07575b0ef315007b92010949f2e31d9b7e3d91bf7e","first_computed_at":"2026-07-05T10:17:30.216667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:30.216667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOf8I70/M0dJZFbV4nhEOwH5e8pp26t9kEvs0YEUv3fFiSxhYcYw+mDjN0dbvLBnFLvjTsWC6lt7D26SRQ2qBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:30.217141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d50c590cfd69999f6deeb4fd23052ef1ffd818171d196977df87619926abcad2","sha256:567581827883d2dd930e988ec7e74b3526c4fbf403f3949c8200476c6383a70f"],"state_sha256":"1005064d23eff574496d20a3cbd763b723fc286d5d36c7a9d867a1feac0e5c08"}