{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J4WGAQPZLQ62TG6WOXSJ72WDVM","short_pith_number":"pith:J4WGAQPZ","schema_version":"1.0","canonical_sha256":"4f2c6041f95c3da99bd675e49feac3ab2b786daf75ca5f53fe4b8ad79f53c6de","source":{"kind":"arxiv","id":"2606.13630","version":1},"attestation_state":"computed","paper":{"title":"From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Olivier Perrotin, Paula Costa, Pedro Correa, Samir Sadok, Thomas Hueber","submitted_at":"2026-06-11T17:41:18Z","abstract_excerpt":"The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units an"},"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":"2606.13630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T17:41:18Z","cross_cats_sorted":[],"title_canon_sha256":"5ffb8e913baea738e58cf65375ebe1de9270736ec206c060206ba2f95c0f9d67","abstract_canon_sha256":"6fb593d85db8eb8047131dc2aa9b414110d51e195a71be56564953986be78466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:16.018530Z","signature_b64":"SrK/jlOa3/T6XPUQxaDX8YSK4Pke4/KIZECIFIuozCdpcIjjAt/+vjUSoxnphBAhgiWtL016SKIBQSvje5fLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f2c6041f95c3da99bd675e49feac3ab2b786daf75ca5f53fe4b8ad79f53c6de","last_reissued_at":"2026-06-12T01:10:16.017724Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:16.017724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Olivier Perrotin, Paula Costa, Pedro Correa, Samir Sadok, Thomas Hueber","submitted_at":"2026-06-11T17:41:18Z","abstract_excerpt":"The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13630","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/2606.13630/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":"2606.13630","created_at":"2026-06-12T01:10:16.017862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13630v1","created_at":"2026-06-12T01:10:16.017862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13630","created_at":"2026-06-12T01:10:16.017862+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4WGAQPZLQ62","created_at":"2026-06-12T01:10:16.017862+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4WGAQPZLQ62TG6W","created_at":"2026-06-12T01:10:16.017862+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4WGAQPZ","created_at":"2026-06-12T01:10:16.017862+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/J4WGAQPZLQ62TG6WOXSJ72WDVM","json":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM.json","graph_json":"https://pith.science/api/pith-number/J4WGAQPZLQ62TG6WOXSJ72WDVM/graph.json","events_json":"https://pith.science/api/pith-number/J4WGAQPZLQ62TG6WOXSJ72WDVM/events.json","paper":"https://pith.science/paper/J4WGAQPZ"},"agent_actions":{"view_html":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM","download_json":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM.json","view_paper":"https://pith.science/paper/J4WGAQPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13630&json=true","fetch_graph":"https://pith.science/api/pith-number/J4WGAQPZLQ62TG6WOXSJ72WDVM/graph.json","fetch_events":"https://pith.science/api/pith-number/J4WGAQPZLQ62TG6WOXSJ72WDVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM/action/storage_attestation","attest_author":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM/action/author_attestation","sign_citation":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM/action/citation_signature","submit_replication":"https://pith.science/pith/J4WGAQPZLQ62TG6WOXSJ72WDVM/action/replication_record"}},"created_at":"2026-06-12T01:10:16.017862+00:00","updated_at":"2026-06-12T01:10:16.017862+00:00"}