{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CW653YQZMBF5MA27IAMFI5GAE2","short_pith_number":"pith:CW653YQZ","schema_version":"1.0","canonical_sha256":"15bddde219604bd6035f40185474c026ab1656598851ed7bda81c0117bb3c6f7","source":{"kind":"arxiv","id":"2510.01832","version":2},"attestation_state":"computed","paper":{"title":"SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2025-10-02T09:27:15Z","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"},"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":"2510.01832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T09:27:15Z","cross_cats_sorted":[],"title_canon_sha256":"f27aa0403a1e495e0f063bde4f2492b01696f98f5318ca6fdb55b70c71624a92","abstract_canon_sha256":"6197e186e2f3c13e5ba7e9d4f77adaabacaa8e384e1498d7133a07dc9a4b87b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-19T00:26:13.238421Z","signature_b64":"WSXA7Zw77RqovmYihZKdqKn8Di31j5OhY8sND1uGAX2W6fdHQLQnAkBPz49biCHHnJv0HnqBMV+uPGstKDnPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15bddde219604bd6035f40185474c026ab1656598851ed7bda81c0117bb3c6f7","last_reissued_at":"2026-08-19T00:26:13.235828Z","signature_status":"signed_v1","first_computed_at":"2026-08-19T00:26:13.235828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2025-10-02T09:27:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01832","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.01832/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2510.01832","created_at":"2026-08-19T00:26:13.236675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.01832v2","created_at":"2026-08-19T00:26:13.236675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01832","created_at":"2026-08-19T00:26:13.236675+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW653YQZMBF5","created_at":"2026-08-19T00:26:13.236675+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW653YQZMBF5MA27","created_at":"2026-08-19T00:26:13.236675+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW653YQZ","created_at":"2026-08-19T00:26:13.236675+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/CW653YQZMBF5MA27IAMFI5GAE2","json":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2.json","graph_json":"https://pith.science/api/pith-number/CW653YQZMBF5MA27IAMFI5GAE2/graph.json","events_json":"https://pith.science/api/pith-number/CW653YQZMBF5MA27IAMFI5GAE2/events.json","paper":"https://pith.science/paper/CW653YQZ"},"agent_actions":{"view_html":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2","download_json":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2.json","view_paper":"https://pith.science/paper/CW653YQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.01832&json=true","fetch_graph":"https://pith.science/api/pith-number/CW653YQZMBF5MA27IAMFI5GAE2/graph.json","fetch_events":"https://pith.science/api/pith-number/CW653YQZMBF5MA27IAMFI5GAE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2/action/storage_attestation","attest_author":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2/action/author_attestation","sign_citation":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2/action/citation_signature","submit_replication":"https://pith.science/pith/CW653YQZMBF5MA27IAMFI5GAE2/action/replication_record"}},"created_at":"2026-08-19T00:26:13.236675+00:00","updated_at":"2026-08-19T00:26:13.236675+00:00"}