{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQU5FA5FF5QSXQMGDSAZXYXR2T","short_pith_number":"pith:TQU5FA5F","schema_version":"1.0","canonical_sha256":"9c29d283a52f612bc1861c819be2f1d4c20f9938fbe603a5e66df977b123a099","source":{"kind":"arxiv","id":"2410.19609","version":1},"attestation_state":"computed","paper":{"title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hongliang He, Hongming Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Wenlin Yao, Zhenzhong Lan","submitted_at":"2024-10-25T15:01:27Z","abstract_excerpt":"The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent open-source efforts have tried to equip agents with the ability to explore environments and continuously improve over time, they are building text-only agents in synthetic environments where the reward signals are clearly defined. Such agents struggle to generalize to realistic settings that require multimodal perception abilities and lack ground-trut"},"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":"2410.19609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T15:01:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd930bcdc0319a159dc763650e6b6268b8091329f3a22a637e27b6832f856ceb","abstract_canon_sha256":"a5b540449a37d6bbb071bc4437d288f474b6b72df4d65058891237e8f4c50ba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:59.197044Z","signature_b64":"ScqxUEDP0R0A54NFbxDdQq8Tb6w2tldc5OcyMPPoECEw+v0gJp0LjQamcgHWFtmrAoSiyG09bEdpAwpvoDCHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c29d283a52f612bc1861c819be2f1d4c20f9938fbe603a5e66df977b123a099","last_reissued_at":"2026-07-05T09:25:59.196548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:59.196548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Hongliang He, Hongming Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Wenlin Yao, Zhenzhong Lan","submitted_at":"2024-10-25T15:01:27Z","abstract_excerpt":"The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent open-source efforts have tried to equip agents with the ability to explore environments and continuously improve over time, they are building text-only agents in synthetic environments where the reward signals are clearly defined. Such agents struggle to generalize to realistic settings that require multimodal perception abilities and lack ground-trut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19609","kind":"arxiv","version":1},"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/2410.19609/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":"2410.19609","created_at":"2026-07-05T09:25:59.196609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19609v1","created_at":"2026-07-05T09:25:59.196609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19609","created_at":"2026-07-05T09:25:59.196609+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQU5FA5FF5QS","created_at":"2026-07-05T09:25:59.196609+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQU5FA5FF5QSXQMG","created_at":"2026-07-05T09:25:59.196609+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQU5FA5F","created_at":"2026-07-05T09:25:59.196609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20398","citing_title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T","json":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T.json","graph_json":"https://pith.science/api/pith-number/TQU5FA5FF5QSXQMGDSAZXYXR2T/graph.json","events_json":"https://pith.science/api/pith-number/TQU5FA5FF5QSXQMGDSAZXYXR2T/events.json","paper":"https://pith.science/paper/TQU5FA5F"},"agent_actions":{"view_html":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T","download_json":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T.json","view_paper":"https://pith.science/paper/TQU5FA5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19609&json=true","fetch_graph":"https://pith.science/api/pith-number/TQU5FA5FF5QSXQMGDSAZXYXR2T/graph.json","fetch_events":"https://pith.science/api/pith-number/TQU5FA5FF5QSXQMGDSAZXYXR2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T/action/storage_attestation","attest_author":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T/action/author_attestation","sign_citation":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T/action/citation_signature","submit_replication":"https://pith.science/pith/TQU5FA5FF5QSXQMGDSAZXYXR2T/action/replication_record"}},"created_at":"2026-07-05T09:25:59.196609+00:00","updated_at":"2026-07-05T09:25:59.196609+00:00"}