{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:77IN72PSPJL4JDCJAFUNZM52CY","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":"1ed4400e527fd8f295d314c80248ca785c030d8e8b8cb3b81627b19d64e9101a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-08T07:27:17Z","title_canon_sha256":"d20eabaaced86977ce170f2f4e1430ed2985ee5bbc0dc6ba19e01057c8ad2445"},"schema_version":"1.0","source":{"id":"2210.03945","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03945","created_at":"2026-07-05T06:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03945v2","created_at":"2026-07-05T06:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03945","created_at":"2026-07-05T06:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"77IN72PSPJL4","created_at":"2026-07-05T06:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"77IN72PSPJL4JDCJ","created_at":"2026-07-05T06:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"77IN72PS","created_at":"2026-07-05T06:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:9d18ff40fc27cffa88416bb7d9206c6c729e01a44be3ed7a32f304f1b598a2f6","target":"graph","created_at":"2026-07-05T06:11:42Z","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/2210.03945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding -- i.e., parsing the raw HTML of a webpage, with applications to automation of web-based tasks, crawling, and browser-assisted retrieval -- have not been fully explored. We contribute HTML understanding models (fine-tuned LLMs) and an in-depth analysis of their capabilities under three tasks: (i) Semantic Classification of HTML elements, (ii) Description Generation for HTML inputs, and (iii) Autonomous Web Navigation of HTML pages. While previou","authors_text":"Aakanksha Chowdhery, Aleksandra Faust, Austin Huang, Izzeddin Gur, Mustafa Safdari, Noah Fiedel, Ofir Nachum, Sharan Narang, Yingjie Miao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-08T07:27:17Z","title":"Understanding HTML with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03945","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":"sha256:75159ff0d35499e063bfa1db6cf052a20a8b8ad30277558bb3340f6a29e13907","target":"record","created_at":"2026-07-05T06:11:42Z","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":"1ed4400e527fd8f295d314c80248ca785c030d8e8b8cb3b81627b19d64e9101a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-08T07:27:17Z","title_canon_sha256":"d20eabaaced86977ce170f2f4e1430ed2985ee5bbc0dc6ba19e01057c8ad2445"},"schema_version":"1.0","source":{"id":"2210.03945","kind":"arxiv","version":2}},"canonical_sha256":"ffd0dfe9f27a57c48c490168dcb3ba161db9116734148ec132c589c27ac87070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffd0dfe9f27a57c48c490168dcb3ba161db9116734148ec132c589c27ac87070","first_computed_at":"2026-07-05T06:11:42.811416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:42.811416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cccxvsd0K8qkwM+ZHgnvL8+u3sBy2JzWaZfZ+cwhewXHvLC4kponakSg/W0ItpfSt6fQXjlWkP71YbOJHnA9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:42.811784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03945","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75159ff0d35499e063bfa1db6cf052a20a8b8ad30277558bb3340f6a29e13907","sha256:9d18ff40fc27cffa88416bb7d9206c6c729e01a44be3ed7a32f304f1b598a2f6"],"state_sha256":"083fa912aa92b69ccc858645fd4933c926de183f1b56170f1d5af51fcffdf8c7"}