{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:22PZPKUFNRYB6DEDGAN7OEL2UT","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":"aa83a6ad47de29776929361af2617fc9be6797aa3191f4a1c9d59e44de77c542","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-01T15:13:49Z","title_canon_sha256":"80b808ecd629231319d779e12c649063f2d461c4e160a64cf08e0836c404a5d2"},"schema_version":"1.0","source":{"id":"2311.00738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00738","created_at":"2026-07-05T07:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00738v1","created_at":"2026-07-05T07:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00738","created_at":"2026-07-05T07:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"22PZPKUFNRYB","created_at":"2026-07-05T07:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"22PZPKUFNRYB6DED","created_at":"2026-07-05T07:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"22PZPKUF","created_at":"2026-07-05T07:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:cdc14ea0a5130c741b7ee002b0ccf9d750d0d8dfaea84b12cf7113c7409662d7","target":"graph","created_at":"2026-07-05T07:08:14Z","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/2311.00738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-01T15:13:49Z","title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00738","kind":"arxiv","version":1},"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":"sha256:2866a3341b8d0a70a7b219d32fbe8164817b86e6a6c1f574b48bcd5fcb66c509","target":"record","created_at":"2026-07-05T07:08:14Z","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":"aa83a6ad47de29776929361af2617fc9be6797aa3191f4a1c9d59e44de77c542","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-01T15:13:49Z","title_canon_sha256":"80b808ecd629231319d779e12c649063f2d461c4e160a64cf08e0836c404a5d2"},"schema_version":"1.0","source":{"id":"2311.00738","kind":"arxiv","version":1}},"canonical_sha256":"d69f97aa856c701f0c83301bf7117aa4fa13cbfde84898f26570e4e66fe1b313","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d69f97aa856c701f0c83301bf7117aa4fa13cbfde84898f26570e4e66fe1b313","first_computed_at":"2026-07-05T07:08:14.722358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:14.722358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NxXX6jK9Odhw/EO5DDRuHKxhJlO9FXlYrv7G1YItdTLep8HN4av2NCabbsjEupW33XZRF9apVY2qPWShhfa4Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:14.722794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2866a3341b8d0a70a7b219d32fbe8164817b86e6a6c1f574b48bcd5fcb66c509","sha256:cdc14ea0a5130c741b7ee002b0ccf9d750d0d8dfaea84b12cf7113c7409662d7"],"state_sha256":"1cf1b3481fa6cef11e1780adbb1acad30baf4e374144a94591d513eaa2bd9dd3"}