{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H5C4TWERWZ3DLAT65L3OUMD6OA","short_pith_number":"pith:H5C4TWER","schema_version":"1.0","canonical_sha256":"3f45c9d891b67635827eeaf6ea307e7013171926ee5efd34375a74fbea04d891","source":{"kind":"arxiv","id":"2308.10897","version":2},"attestation_state":"computed","paper":{"title":"Can Language Models Learn to Listen?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Dan Klein, Evonne Ng, Sanjay Subramanian, Shiry Ginosar, Trevor Darrell","submitted_at":"2023-08-21T17:59:02Z","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"},"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":"2308.10897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"604d454f7bc8b8ebca8c9e1864327394d4023b1bdc1eb7e6defd2f60d7756822","abstract_canon_sha256":"d061bfa2ebc7add1e173efa390ab122091f2f21196f52ed4ffe06b83df3172c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:43.004734Z","signature_b64":"vnLrKXznG/mUIbz7oydvEQJsScfssNzLg9BAaMQZLJyPUNGSMjXtJTPRSEL01VtgsEC4zbBFN8vPSViHwxG0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f45c9d891b67635827eeaf6ea307e7013171926ee5efd34375a74fbea04d891","last_reissued_at":"2026-06-05T00:13:43.002492Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:43.002492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Language Models Learn to Listen?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Dan Klein, Evonne Ng, Sanjay Subramanian, Shiry Ginosar, Trevor Darrell","submitted_at":"2023-08-21T17:59:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10897","kind":"arxiv","version":2},"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/2308.10897/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":"2308.10897","created_at":"2026-06-05T00:13:43.002587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10897v2","created_at":"2026-06-05T00:13:43.002587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10897","created_at":"2026-06-05T00:13:43.002587+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5C4TWERWZ3D","created_at":"2026-06-05T00:13:43.002587+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5C4TWERWZ3DLAT6","created_at":"2026-06-05T00:13:43.002587+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5C4TWER","created_at":"2026-06-05T00:13:43.002587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA","json":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA.json","graph_json":"https://pith.science/api/pith-number/H5C4TWERWZ3DLAT65L3OUMD6OA/graph.json","events_json":"https://pith.science/api/pith-number/H5C4TWERWZ3DLAT65L3OUMD6OA/events.json","paper":"https://pith.science/paper/H5C4TWER"},"agent_actions":{"view_html":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA","download_json":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA.json","view_paper":"https://pith.science/paper/H5C4TWER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/H5C4TWERWZ3DLAT65L3OUMD6OA/graph.json","fetch_events":"https://pith.science/api/pith-number/H5C4TWERWZ3DLAT65L3OUMD6OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA/action/storage_attestation","attest_author":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA/action/author_attestation","sign_citation":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA/action/citation_signature","submit_replication":"https://pith.science/pith/H5C4TWERWZ3DLAT65L3OUMD6OA/action/replication_record"}},"created_at":"2026-06-05T00:13:43.002587+00:00","updated_at":"2026-06-05T00:13:43.002587+00:00"}