{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ILUY5LTU57ZL4OD77JKI2C65SW","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":"2fe5e6b9ee2b739e6a8552b172499cf658eb354b4e1a52a66c1d12ce12f70c8f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-19T17:44:34Z","title_canon_sha256":"1c44c120f0843ffb15c1a06f57c527fa0ebbbd101cfe9b95e4e6f019c81f5b53"},"schema_version":"1.0","source":{"id":"2305.11854","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11854","created_at":"2026-07-05T07:48:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11854v4","created_at":"2026-07-05T07:48:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11854","created_at":"2026-07-05T07:48:46Z"},{"alias_kind":"pith_short_12","alias_value":"ILUY5LTU57ZL","created_at":"2026-07-05T07:48:46Z"},{"alias_kind":"pith_short_16","alias_value":"ILUY5LTU57ZL4OD7","created_at":"2026-07-05T07:48:46Z"},{"alias_kind":"pith_short_8","alias_value":"ILUY5LTU","created_at":"2026-07-05T07:48:46Z"}],"graph_snapshots":[{"event_id":"sha256:9f7ee9c6e1069b6d9f324f7cbbfa0088a6311c60e2244cdff09ef295eb17374c","target":"graph","created_at":"2026-07-05T07:48:46Z","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/2305.11854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The progress of autonomous web navigation has been hindered by the dependence on billions of exploratory interactions via online reinforcement learning, and domain-specific model designs that make it difficult to leverage generalization from rich out-of-domain data. In this work, we study data-driven offline training for web agents with vision-language foundation models. We propose an instruction-following multimodal agent, WebGUM, that observes both webpage screenshots and HTML pages and outputs web navigation actions, such as click and type. WebGUM is trained by jointly finetuning an instruc","authors_text":"Aleksandra Faust, Hiroki Furuta, Izzeddin Gur, Kuang-Huei Lee, Ofir Nachum, Shixiang Shane Gu, Yutaka Matsuo","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-19T17:44:34Z","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11854","kind":"arxiv","version":4},"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":"sha256:9803b3bb3d7a517d844223e144d17b6603ff13de79f0f116396002aab1ed1c8b","target":"record","created_at":"2026-07-05T07:48:46Z","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":"2fe5e6b9ee2b739e6a8552b172499cf658eb354b4e1a52a66c1d12ce12f70c8f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-19T17:44:34Z","title_canon_sha256":"1c44c120f0843ffb15c1a06f57c527fa0ebbbd101cfe9b95e4e6f019c81f5b53"},"schema_version":"1.0","source":{"id":"2305.11854","kind":"arxiv","version":4}},"canonical_sha256":"42e98eae74eff2be387ffa548d0bdd95adc7dc9b04b180adf1847992ce2e1935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42e98eae74eff2be387ffa548d0bdd95adc7dc9b04b180adf1847992ce2e1935","first_computed_at":"2026-07-05T07:48:46.459345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:46.459345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rXLSaEyDWRby8hf0sXllc4VDLYulmXokaud8RUMk0Hltzt5RkYiJK7GRnBXRkI27YCKGtc+mL1eo3yPI2BKkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:46.459857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11854","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9803b3bb3d7a517d844223e144d17b6603ff13de79f0f116396002aab1ed1c8b","sha256:9f7ee9c6e1069b6d9f324f7cbbfa0088a6311c60e2244cdff09ef295eb17374c"],"state_sha256":"c982c21fe83e241b843f663e607153178a84e6c6ba0a19d551759a72ce6859d1"}