{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CYK2QWRLI37ADTYAZEIKX4RNOQ","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":"04bb364cf4de418f8ba308847cf648c866463f6b624afc83eaba93fc7860a0c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-19T09:59:44Z","title_canon_sha256":"7d1a3c7b7573c0f502fe865fee0c79344746332ec15796e609c1bd4c9d69de20"},"schema_version":"1.0","source":{"id":"2404.12753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12753","created_at":"2026-07-05T09:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12753v2","created_at":"2026-07-05T09:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12753","created_at":"2026-07-05T09:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"CYK2QWRLI37A","created_at":"2026-07-05T09:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"CYK2QWRLI37ADTYA","created_at":"2026-07-05T09:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"CYK2QWRL","created_at":"2026-07-05T09:12:05Z"}],"graph_snapshots":[{"event_id":"sha256:c2cd17e240cc8aef0ea9982176b9c7eb819ed31b7bb4cc751267a7c39297a8b6","target":"graph","created_at":"2026-07-05T09:12:05Z","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/2404.12753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from limited adaptability and scalability when faced with a new website, while language agents, empowered by large language models (LLMs), exhibit poor reusability in diverse web environments. In this work, we introduce the paradigm of generating web scrapers with LLMs and propose AutoScraper, a two-stage framework that can handle diverse and changing web environ","authors_text":"Chenghao Peng, Jiaqing Liang, Liqian Wen, Wenhao Huang, Yanghua Xiao, Zhixu Li, Zhouhong Gu, Zulong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-19T09:59:44Z","title":"AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12753","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:fb91ffad319c36c77ae98baee19ce7ab786d82d4a07375cd56ab55b424ee192e","target":"record","created_at":"2026-07-05T09:12:05Z","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":"04bb364cf4de418f8ba308847cf648c866463f6b624afc83eaba93fc7860a0c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-19T09:59:44Z","title_canon_sha256":"7d1a3c7b7573c0f502fe865fee0c79344746332ec15796e609c1bd4c9d69de20"},"schema_version":"1.0","source":{"id":"2404.12753","kind":"arxiv","version":2}},"canonical_sha256":"1615a85a2b46fe01cf00c910abf22d742eb8c20a91f662be140a66ac3f2b0eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1615a85a2b46fe01cf00c910abf22d742eb8c20a91f662be140a66ac3f2b0eca","first_computed_at":"2026-07-05T09:12:05.789254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:05.789254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DIV1evFzaLuG4GjgXpYNlkLAl8AB/lL+KI1aTPfvIG19a7a4vA5/v/L+5gfiOf/nf6LqQrGByXNFyb1HrT3iAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:05.790608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb91ffad319c36c77ae98baee19ce7ab786d82d4a07375cd56ab55b424ee192e","sha256:c2cd17e240cc8aef0ea9982176b9c7eb819ed31b7bb4cc751267a7c39297a8b6"],"state_sha256":"07f4cd1b11fc5dea61142119f73241a2dac81ce94543215e02901520fdf8ce38"}