{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:77IN72PSPJL4JDCJAFUNZM52CY","short_pith_number":"pith:77IN72PS","schema_version":"1.0","canonical_sha256":"ffd0dfe9f27a57c48c490168dcb3ba161db9116734148ec132c589c27ac87070","source":{"kind":"arxiv","id":"2210.03945","version":2},"attestation_state":"computed","paper":{"title":"Understanding HTML with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aakanksha Chowdhery, Aleksandra Faust, Austin Huang, Izzeddin Gur, Mustafa Safdari, Noah Fiedel, Ofir Nachum, Sharan Narang, Yingjie Miao","submitted_at":"2022-10-08T07:27:17Z","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"},"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":"2210.03945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-08T07:27:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d20eabaaced86977ce170f2f4e1430ed2985ee5bbc0dc6ba19e01057c8ad2445","abstract_canon_sha256":"1ed4400e527fd8f295d314c80248ca785c030d8e8b8cb3b81627b19d64e9101a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:42.811784Z","signature_b64":"cccxvsd0K8qkwM+ZHgnvL8+u3sBy2JzWaZfZ+cwhewXHvLC4kponakSg/W0ItpfSt6fQXjlWkP71YbOJHnA9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffd0dfe9f27a57c48c490168dcb3ba161db9116734148ec132c589c27ac87070","last_reissued_at":"2026-07-05T06:11:42.811416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:42.811416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding HTML with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aakanksha Chowdhery, Aleksandra Faust, Austin Huang, Izzeddin Gur, Mustafa Safdari, Noah Fiedel, Ofir Nachum, Sharan Narang, Yingjie Miao","submitted_at":"2022-10-08T07:27:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03945","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/2210.03945/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":"2210.03945","created_at":"2026-07-05T06:11:42.811475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03945v2","created_at":"2026-07-05T06:11:42.811475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03945","created_at":"2026-07-05T06:11:42.811475+00:00"},{"alias_kind":"pith_short_12","alias_value":"77IN72PSPJL4","created_at":"2026-07-05T06:11:42.811475+00:00"},{"alias_kind":"pith_short_16","alias_value":"77IN72PSPJL4JDCJ","created_at":"2026-07-05T06:11:42.811475+00:00"},{"alias_kind":"pith_short_8","alias_value":"77IN72PS","created_at":"2026-07-05T06:11:42.811475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16565","citing_title":"Skim: Speculative Execution for Fast and Efficient Web Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17491","citing_title":"Language Models can Solve Computer Tasks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY","json":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY.json","graph_json":"https://pith.science/api/pith-number/77IN72PSPJL4JDCJAFUNZM52CY/graph.json","events_json":"https://pith.science/api/pith-number/77IN72PSPJL4JDCJAFUNZM52CY/events.json","paper":"https://pith.science/paper/77IN72PS"},"agent_actions":{"view_html":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY","download_json":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY.json","view_paper":"https://pith.science/paper/77IN72PS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03945&json=true","fetch_graph":"https://pith.science/api/pith-number/77IN72PSPJL4JDCJAFUNZM52CY/graph.json","fetch_events":"https://pith.science/api/pith-number/77IN72PSPJL4JDCJAFUNZM52CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY/action/storage_attestation","attest_author":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY/action/author_attestation","sign_citation":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY/action/citation_signature","submit_replication":"https://pith.science/pith/77IN72PSPJL4JDCJAFUNZM52CY/action/replication_record"}},"created_at":"2026-07-05T06:11:42.811475+00:00","updated_at":"2026-07-05T06:11:42.811475+00:00"}