{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LI7Y53MTOWLXE2DMEKXH7K2O6W","short_pith_number":"pith:LI7Y53MT","schema_version":"1.0","canonical_sha256":"5a3f8eed93759772686c22ae7fab4ef5b85919b4bebc340e888d036798314769","source":{"kind":"arxiv","id":"2606.01031","version":1},"attestation_state":"computed","paper":{"title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.GR","authors_text":"Lei Wang, Yongsheng Gao, Yu Zhang, Zhicheng Zhang","submitted_at":"2026-05-31T05:44:42Z","abstract_excerpt":"Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos. This assumption does not match speech-driven facial motion, which naturally includes slight timing shifts, different speaking speeds, and stylistic variations. As a result, conventional metrics may treat harmless timing differences as quality errors, making it harder to fairly compare methods and understand their trade-offs. In this work, we argue that evaluation of dynamic generative mo"},"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":"2606.01031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-05-31T05:44:42Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"7ca09ed123a763399890ddd922778c92ebd91e6aa4c834ab7e59e9c3b2fb075a","abstract_canon_sha256":"7c5f922dede4b500d860bc5a1fb1454da52561bad03a3a05bc88db5b008df3ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:19.035107Z","signature_b64":"6Aev+3sxgA4DYu1/5zbwMPu1dnIsjnagH908qLztfB4PYtwpRpqiVKZ2s7dPKiG+ZyojgIR8Z0r9kRJ0/OuyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a3f8eed93759772686c22ae7fab4ef5b85919b4bebc340e888d036798314769","last_reissued_at":"2026-06-02T01:04:19.034694Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:19.034694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.GR","authors_text":"Lei Wang, Yongsheng Gao, Yu Zhang, Zhicheng Zhang","submitted_at":"2026-05-31T05:44:42Z","abstract_excerpt":"Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos. This assumption does not match speech-driven facial motion, which naturally includes slight timing shifts, different speaking speeds, and stylistic variations. As a result, conventional metrics may treat harmless timing differences as quality errors, making it harder to fairly compare methods and understand their trade-offs. In this work, we argue that evaluation of dynamic generative mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01031","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/2606.01031/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":"2606.01031","created_at":"2026-06-02T01:04:19.034753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01031v1","created_at":"2026-06-02T01:04:19.034753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01031","created_at":"2026-06-02T01:04:19.034753+00:00"},{"alias_kind":"pith_short_12","alias_value":"LI7Y53MTOWLX","created_at":"2026-06-02T01:04:19.034753+00:00"},{"alias_kind":"pith_short_16","alias_value":"LI7Y53MTOWLXE2DM","created_at":"2026-06-02T01:04:19.034753+00:00"},{"alias_kind":"pith_short_8","alias_value":"LI7Y53MT","created_at":"2026-06-02T01:04:19.034753+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/LI7Y53MTOWLXE2DMEKXH7K2O6W","json":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W.json","graph_json":"https://pith.science/api/pith-number/LI7Y53MTOWLXE2DMEKXH7K2O6W/graph.json","events_json":"https://pith.science/api/pith-number/LI7Y53MTOWLXE2DMEKXH7K2O6W/events.json","paper":"https://pith.science/paper/LI7Y53MT"},"agent_actions":{"view_html":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W","download_json":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W.json","view_paper":"https://pith.science/paper/LI7Y53MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01031&json=true","fetch_graph":"https://pith.science/api/pith-number/LI7Y53MTOWLXE2DMEKXH7K2O6W/graph.json","fetch_events":"https://pith.science/api/pith-number/LI7Y53MTOWLXE2DMEKXH7K2O6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W/action/storage_attestation","attest_author":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W/action/author_attestation","sign_citation":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W/action/citation_signature","submit_replication":"https://pith.science/pith/LI7Y53MTOWLXE2DMEKXH7K2O6W/action/replication_record"}},"created_at":"2026-06-02T01:04:19.034753+00:00","updated_at":"2026-06-02T01:04:19.034753+00:00"}