{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H5C4TWERWZ3DLAT65L3OUMD6OA","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":"d061bfa2ebc7add1e173efa390ab122091f2f21196f52ed4ffe06b83df3172c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T17:59:02Z","title_canon_sha256":"604d454f7bc8b8ebca8c9e1864327394d4023b1bdc1eb7e6defd2f60d7756822"},"schema_version":"1.0","source":{"id":"2308.10897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10897","created_at":"2026-06-05T00:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10897v2","created_at":"2026-06-05T00:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10897","created_at":"2026-06-05T00:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"H5C4TWERWZ3D","created_at":"2026-06-05T00:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"H5C4TWERWZ3DLAT6","created_at":"2026-06-05T00:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"H5C4TWER","created_at":"2026-06-05T00:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:3055aeac74f0754b9833b9d7ca7c6906feb1bfcf7cbf7fffa03c77f94c1b40db","target":"graph","created_at":"2026-06-05T00:13:43Z","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/2308.10897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the speaker's words with their timestamps, our approach autoregressively predicts a response of a listener: a sequence of listener facial gestures, quantized using a VQ-VAE. Since gesture is a language component, we propose treating the quantized atomic motion elements as additional language token inputs to a transformer-based large language model. Initializing our transformer with the weights of a language model pre-trai","authors_text":"Angjoo Kanazawa, Dan Klein, Evonne Ng, Sanjay Subramanian, Shiry Ginosar, Trevor Darrell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T17:59:02Z","title":"Can Language Models Learn to Listen?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10897","kind":"arxiv","version":2},"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:d7ba4f516960ba8fad9f3ce32aef27a15806ca60ac6163e6fb2e55bb7b79de00","target":"record","created_at":"2026-06-05T00:13:43Z","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":"d061bfa2ebc7add1e173efa390ab122091f2f21196f52ed4ffe06b83df3172c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T17:59:02Z","title_canon_sha256":"604d454f7bc8b8ebca8c9e1864327394d4023b1bdc1eb7e6defd2f60d7756822"},"schema_version":"1.0","source":{"id":"2308.10897","kind":"arxiv","version":2}},"canonical_sha256":"3f45c9d891b67635827eeaf6ea307e7013171926ee5efd34375a74fbea04d891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f45c9d891b67635827eeaf6ea307e7013171926ee5efd34375a74fbea04d891","first_computed_at":"2026-06-05T00:13:43.002492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:43.002492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vnLrKXznG/mUIbz7oydvEQJsScfssNzLg9BAaMQZLJyPUNGSMjXtJTPRSEL01VtgsEC4zbBFN8vPSViHwxG0DQ==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:43.004734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7ba4f516960ba8fad9f3ce32aef27a15806ca60ac6163e6fb2e55bb7b79de00","sha256:3055aeac74f0754b9833b9d7ca7c6906feb1bfcf7cbf7fffa03c77f94c1b40db"],"state_sha256":"ce626308893dda47db462a977a62e85c6bf59fa69556afbd61113f81a8503dfb"}