{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CW653YQZMBF5MA27IAMFI5GAE2","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":"6197e186e2f3c13e5ba7e9d4f77adaabacaa8e384e1498d7133a07dc9a4b87b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T09:27:15Z","title_canon_sha256":"f27aa0403a1e495e0f063bde4f2492b01696f98f5318ca6fdb55b70c71624a92"},"schema_version":"1.0","source":{"id":"2510.01832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01832","created_at":"2026-08-19T00:26:13Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01832v2","created_at":"2026-08-19T00:26:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01832","created_at":"2026-08-19T00:26:13Z"},{"alias_kind":"pith_short_12","alias_value":"CW653YQZMBF5","created_at":"2026-08-19T00:26:13Z"},{"alias_kind":"pith_short_16","alias_value":"CW653YQZMBF5MA27","created_at":"2026-08-19T00:26:13Z"},{"alias_kind":"pith_short_8","alias_value":"CW653YQZ","created_at":"2026-08-19T00:26:13Z"}],"graph_snapshots":[{"event_id":"sha256:01359a7026650ae4e42b38ea99964dd1bb9611ed2995eeb965e33e2e1026b599","target":"graph","created_at":"2026-08-19T00:26:13Z","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/2510.01832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging. Existing methods either lack generalization or are resource-intensive due to per-page LLM inference. In this paper, we introduce SCRIBES (SCRIpt-Based Semi-Structured Content Extraction at Web-Scale), a novel reinforcement learning framework that leverages layout similarity across webpages within the same site as a reward signal. Instead of processing each pag","authors_text":"Anuj Kumar, Kai Sun, Lisheng Fu, Rulin Shao, Shicheng Liu, Wen-tau Yih, Xilun Chen, Xin Luna Dong, Xinyuan Zhang, Yue Liu, Zhaojiang Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T09:27:15Z","title":"SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01832","kind":"arxiv","version":2},"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:f7195a3bd81911bd1a0de5c077752190de55953c154836c7d293c45feb786d8f","target":"record","created_at":"2026-08-19T00:26:13Z","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":"6197e186e2f3c13e5ba7e9d4f77adaabacaa8e384e1498d7133a07dc9a4b87b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T09:27:15Z","title_canon_sha256":"f27aa0403a1e495e0f063bde4f2492b01696f98f5318ca6fdb55b70c71624a92"},"schema_version":"1.0","source":{"id":"2510.01832","kind":"arxiv","version":2}},"canonical_sha256":"15bddde219604bd6035f40185474c026ab1656598851ed7bda81c0117bb3c6f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15bddde219604bd6035f40185474c026ab1656598851ed7bda81c0117bb3c6f7","first_computed_at":"2026-08-19T00:26:13.235828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-19T00:26:13.235828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WSXA7Zw77RqovmYihZKdqKn8Di31j5OhY8sND1uGAX2W6fdHQLQnAkBPz49biCHHnJv0HnqBMV+uPGstKDnPCA==","signature_status":"signed_v1","signed_at":"2026-08-19T00:26:13.238421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7195a3bd81911bd1a0de5c077752190de55953c154836c7d293c45feb786d8f","sha256:01359a7026650ae4e42b38ea99964dd1bb9611ed2995eeb965e33e2e1026b599"],"state_sha256":"08334c96332b3f0bd45a19ac39936ee78f24489958bd490af309008b7d5ed8a1"}