{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CEHJDTZV2I7YBDWNS3NOOPDJ7K","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":"f9c11ac1aaeccf8821eff5f62635f71947ba29494ffb9f72f898edc48f81c6cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T17:58:04Z","title_canon_sha256":"9c95414e59422105b2ef9f1788d2e4e1b13692827547a6bf6837c8bad9624d67"},"schema_version":"1.0","source":{"id":"2204.08451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08451","created_at":"2026-07-05T04:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08451v1","created_at":"2026-07-05T04:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08451","created_at":"2026-07-05T04:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"CEHJDTZV2I7Y","created_at":"2026-07-05T04:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"CEHJDTZV2I7YBDWN","created_at":"2026-07-05T04:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"CEHJDTZV","created_at":"2026-07-05T04:15:26Z"}],"graph_snapshots":[{"event_id":"sha256:d9bf782a24326be42b308c754c6c4dc0663baaa6e7affc8475dec49cb8ea1e7d","target":"graph","created_at":"2026-07-05T04:15:26Z","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/2204.08451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and speech audio of the speaker using a motion-audio cross attention transformer. Furthermore, we enable non-deterministic prediction by learning a discrete latent representation of realistic listener motion with a novel motion-encoding VQ-VAE. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions. Moreover, it","authors_text":"Angjoo Kanazawa, Evonne Ng, Hanbyul Joo, Hao Li, Liwen Hu, Shiry Ginosar, Trevor Darrell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T17:58:04Z","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08451","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:bc536dd91bca29527a64751690f63cc6eae47633ee726e4677f25004b9b62995","target":"record","created_at":"2026-07-05T04:15:26Z","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":"f9c11ac1aaeccf8821eff5f62635f71947ba29494ffb9f72f898edc48f81c6cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-18T17:58:04Z","title_canon_sha256":"9c95414e59422105b2ef9f1788d2e4e1b13692827547a6bf6837c8bad9624d67"},"schema_version":"1.0","source":{"id":"2204.08451","kind":"arxiv","version":1}},"canonical_sha256":"110e91cf35d23f808ecd96dae73c69fa84279a2a6e1ebdc5797e452727728920","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"110e91cf35d23f808ecd96dae73c69fa84279a2a6e1ebdc5797e452727728920","first_computed_at":"2026-07-05T04:15:26.231018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:26.231018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gMHN6q9lpt62ePNhkaVOFtMW/uOv1fTFEqUgd0hzDDtVKLyihs9WsP5Lq2Dyy29NIsSCDJ3df3H1MzmvjG3wBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:26.231518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc536dd91bca29527a64751690f63cc6eae47633ee726e4677f25004b9b62995","sha256:d9bf782a24326be42b308c754c6c4dc0663baaa6e7affc8475dec49cb8ea1e7d"],"state_sha256":"ba16853fd84884d17b19ac2eba00f9827e5fff6802e673f17d4dc1c4efb1210f"}