{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:22PZPKUFNRYB6DEDGAN7OEL2UT","short_pith_number":"pith:22PZPKUF","schema_version":"1.0","canonical_sha256":"d69f97aa856c701f0c83301bf7117aa4fa13cbfde84898f26570e4e66fe1b313","source":{"kind":"arxiv","id":"2311.00738","version":1},"attestation_state":"computed","paper":{"title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Alexander De La Iglesia, Itamar Bar-Yossef, Joyce Chai, Keunwoo Peter Yu, Megan Su, Shane Storks, Xiao Lin Zheng, Yichi Zhang, Yuwei Bao","submitted_at":"2023-11-01T15:13:49Z","abstract_excerpt":"Despite tremendous advances in AI, it remains a significant challenge to develop interactive task guidance systems that can offer situated, personalized guidance and assist humans in various tasks. These systems need to have a sophisticated understanding of the user as well as the environment, and make timely accurate decisions on when and what to say. To address this issue, we created a new multimodal benchmark dataset, Watch, Talk and Guide (WTaG) based on natural interaction between a human user and a human instructor. We further proposed two tasks: User and Environment Understanding, and I"},"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":"2311.00738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-01T15:13:49Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"80b808ecd629231319d779e12c649063f2d461c4e160a64cf08e0836c404a5d2","abstract_canon_sha256":"aa83a6ad47de29776929361af2617fc9be6797aa3191f4a1c9d59e44de77c542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:14.722794Z","signature_b64":"NxXX6jK9Odhw/EO5DDRuHKxhJlO9FXlYrv7G1YItdTLep8HN4av2NCabbsjEupW33XZRF9apVY2qPWShhfa4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d69f97aa856c701f0c83301bf7117aa4fa13cbfde84898f26570e4e66fe1b313","last_reissued_at":"2026-07-05T07:08:14.722358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:14.722358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Alexander De La Iglesia, Itamar Bar-Yossef, Joyce Chai, Keunwoo Peter Yu, Megan Su, Shane Storks, Xiao Lin Zheng, Yichi Zhang, Yuwei Bao","submitted_at":"2023-11-01T15:13:49Z","abstract_excerpt":"Despite tremendous advances in AI, it remains a significant challenge to develop interactive task guidance systems that can offer situated, personalized guidance and assist humans in various tasks. These systems need to have a sophisticated understanding of the user as well as the environment, and make timely accurate decisions on when and what to say. To address this issue, we created a new multimodal benchmark dataset, Watch, Talk and Guide (WTaG) based on natural interaction between a human user and a human instructor. We further proposed two tasks: User and Environment Understanding, and I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00738","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/2311.00738/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":"2311.00738","created_at":"2026-07-05T07:08:14.722415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00738v1","created_at":"2026-07-05T07:08:14.722415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00738","created_at":"2026-07-05T07:08:14.722415+00:00"},{"alias_kind":"pith_short_12","alias_value":"22PZPKUFNRYB","created_at":"2026-07-05T07:08:14.722415+00:00"},{"alias_kind":"pith_short_16","alias_value":"22PZPKUFNRYB6DED","created_at":"2026-07-05T07:08:14.722415+00:00"},{"alias_kind":"pith_short_8","alias_value":"22PZPKUF","created_at":"2026-07-05T07:08:14.722415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05904","citing_title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT","json":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT.json","graph_json":"https://pith.science/api/pith-number/22PZPKUFNRYB6DEDGAN7OEL2UT/graph.json","events_json":"https://pith.science/api/pith-number/22PZPKUFNRYB6DEDGAN7OEL2UT/events.json","paper":"https://pith.science/paper/22PZPKUF"},"agent_actions":{"view_html":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT","download_json":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT.json","view_paper":"https://pith.science/paper/22PZPKUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00738&json=true","fetch_graph":"https://pith.science/api/pith-number/22PZPKUFNRYB6DEDGAN7OEL2UT/graph.json","fetch_events":"https://pith.science/api/pith-number/22PZPKUFNRYB6DEDGAN7OEL2UT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT/action/storage_attestation","attest_author":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT/action/author_attestation","sign_citation":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT/action/citation_signature","submit_replication":"https://pith.science/pith/22PZPKUFNRYB6DEDGAN7OEL2UT/action/replication_record"}},"created_at":"2026-07-05T07:08:14.722415+00:00","updated_at":"2026-07-05T07:08:14.722415+00:00"}