{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TSH7LS6M3WL5RD5C5SC5I4YUFV","short_pith_number":"pith:TSH7LS6M","schema_version":"1.0","canonical_sha256":"9c8ff5cbccdd97d88fa2ec85d473142d6ff3f085a68c3501bb57e2b0bec4ec3c","source":{"kind":"arxiv","id":"2506.15677","version":3},"attestation_state":"computed","paper":{"title":"Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alexander Chien, Bingxuan Li, Da Yin, Kai-Wei Chang, Maxine Wu, Rui Sun, Xingcheng Yao, Ying Nian Wu, Yining Hong, Zhecan James Wang","submitted_at":"2025-06-18T17:58:17Z","abstract_excerpt":"AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoni"},"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":"2506.15677","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-18T17:58:17Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","cs.RO"],"title_canon_sha256":"b17cc1d6d841f8adbff361e4c53658189974417d21414216af142663d0240140","abstract_canon_sha256":"96fcab92ea44f2347f903129c050215d424b7da105ce8f09bb62de12d701e066"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:15.086819Z","signature_b64":"y3KF9n9UHOasiHbxtRFjRoGUbKvS97nmRfBOrnWJDv8GnZG4h+3X0yKXQNKVzkYcEKZ2RuwvXPYba7Oa2+cQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8ff5cbccdd97d88fa2ec85d473142d6ff3f085a68c3501bb57e2b0bec4ec3c","last_reissued_at":"2026-07-05T11:45:15.086306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:15.086306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alexander Chien, Bingxuan Li, Da Yin, Kai-Wei Chang, Maxine Wu, Rui Sun, Xingcheng Yao, Ying Nian Wu, Yining Hong, Zhecan James Wang","submitted_at":"2025-06-18T17:58:17Z","abstract_excerpt":"AI agents today are mostly siloed - they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action - but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce Embodied Web Agents, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15677","kind":"arxiv","version":3},"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/2506.15677/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":"2506.15677","created_at":"2026-07-05T11:45:15.086371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15677v3","created_at":"2026-07-05T11:45:15.086371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15677","created_at":"2026-07-05T11:45:15.086371+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSH7LS6M3WL5","created_at":"2026-07-05T11:45:15.086371+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSH7LS6M3WL5RD5C","created_at":"2026-07-05T11:45:15.086371+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSH7LS6M","created_at":"2026-07-05T11:45:15.086371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV","json":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV.json","graph_json":"https://pith.science/api/pith-number/TSH7LS6M3WL5RD5C5SC5I4YUFV/graph.json","events_json":"https://pith.science/api/pith-number/TSH7LS6M3WL5RD5C5SC5I4YUFV/events.json","paper":"https://pith.science/paper/TSH7LS6M"},"agent_actions":{"view_html":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV","download_json":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV.json","view_paper":"https://pith.science/paper/TSH7LS6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15677&json=true","fetch_graph":"https://pith.science/api/pith-number/TSH7LS6M3WL5RD5C5SC5I4YUFV/graph.json","fetch_events":"https://pith.science/api/pith-number/TSH7LS6M3WL5RD5C5SC5I4YUFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV/action/storage_attestation","attest_author":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV/action/author_attestation","sign_citation":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV/action/citation_signature","submit_replication":"https://pith.science/pith/TSH7LS6M3WL5RD5C5SC5I4YUFV/action/replication_record"}},"created_at":"2026-07-05T11:45:15.086371+00:00","updated_at":"2026-07-05T11:45:15.086371+00:00"}