{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I7GG5VQRYUCI46XZYQGKCUK46P","short_pith_number":"pith:I7GG5VQR","schema_version":"1.0","canonical_sha256":"47cc6ed611c5048e7af9c40ca1515cf3dc54a87fc0f6cf3399d58a9852b4f56d","source":{"kind":"arxiv","id":"2404.03648","version":2},"attestation_state":"computed","paper":{"title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanchen Zhang, Hanyu Lai, Hao Yu, Iat Long Iong, Jie Tang, Pengbo Shen, Shuntian Yao, Xiaohan Zhang, Xiao Liu, Yuxiao Dong, Yuxuan Chen","submitted_at":"2024-04-04T17:58:40Z","abstract_excerpt":"Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web. In light of these challenges, we develop the open AutoWebGLM based on ChatGLM3-6B. AutoWebGLM can serve as a powerful automated web navigation agent that outperform GPT-4. Inspired by human browsing patterns, we first design an HTML simplification algorithm to represent webpages"},"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":"2404.03648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:58:40Z","cross_cats_sorted":[],"title_canon_sha256":"d8429aadb528f67fd869eec347674259a938f8630250bddc5d6e0b8adc5bf434","abstract_canon_sha256":"06f902a4201f255d43e66dd6c9204efcea64e423a8c166857c4aec821a57eceb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:27.747720Z","signature_b64":"T9YpV7zJknf27H1BWNEDUKK03q1C8DAoDCItwqV9waUZYS7c9VI88xGwG3I/tZK3a3irjQOSx6qQyIdNv4s1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47cc6ed611c5048e7af9c40ca1515cf3dc54a87fc0f6cf3399d58a9852b4f56d","last_reissued_at":"2026-07-05T09:19:27.747223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:27.747223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanchen Zhang, Hanyu Lai, Hao Yu, Iat Long Iong, Jie Tang, Pengbo Shen, Shuntian Yao, Xiaohan Zhang, Xiao Liu, Yuxiao Dong, Yuxuan Chen","submitted_at":"2024-04-04T17:58:40Z","abstract_excerpt":"Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web. In light of these challenges, we develop the open AutoWebGLM based on ChatGLM3-6B. AutoWebGLM can serve as a powerful automated web navigation agent that outperform GPT-4. Inspired by human browsing patterns, we first design an HTML simplification algorithm to represent webpages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03648","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/2404.03648/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":"2404.03648","created_at":"2026-07-05T09:19:27.747282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03648v2","created_at":"2026-07-05T09:19:27.747282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03648","created_at":"2026-07-05T09:19:27.747282+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7GG5VQRYUCI","created_at":"2026-07-05T09:19:27.747282+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7GG5VQRYUCI46XZ","created_at":"2026-07-05T09:19:27.747282+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7GG5VQR","created_at":"2026-07-05T09:19:27.747282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12373","citing_title":"WebCanvas: Benchmarking Web Agents in Online Environments","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04454","citing_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12793","citing_title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P","json":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P.json","graph_json":"https://pith.science/api/pith-number/I7GG5VQRYUCI46XZYQGKCUK46P/graph.json","events_json":"https://pith.science/api/pith-number/I7GG5VQRYUCI46XZYQGKCUK46P/events.json","paper":"https://pith.science/paper/I7GG5VQR"},"agent_actions":{"view_html":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P","download_json":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P.json","view_paper":"https://pith.science/paper/I7GG5VQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03648&json=true","fetch_graph":"https://pith.science/api/pith-number/I7GG5VQRYUCI46XZYQGKCUK46P/graph.json","fetch_events":"https://pith.science/api/pith-number/I7GG5VQRYUCI46XZYQGKCUK46P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P/action/storage_attestation","attest_author":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P/action/author_attestation","sign_citation":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P/action/citation_signature","submit_replication":"https://pith.science/pith/I7GG5VQRYUCI46XZYQGKCUK46P/action/replication_record"}},"created_at":"2026-07-05T09:19:27.747282+00:00","updated_at":"2026-07-05T09:19:27.747282+00:00"}