{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43TEZSGC5XVHSEEZN64R4PJKJS","short_pith_number":"pith:43TEZSGC","schema_version":"1.0","canonical_sha256":"e6e64cc8c2edea7910996fb91e3d2a4ca3607d951b4e34d35992295a5dc0ec56","source":{"kind":"arxiv","id":"2605.25488","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lei Wang, Yongsheng Gao, Yu Zhang, Zhicheng Zhang","submitted_at":"2026-05-25T06:45:29Z","abstract_excerpt":"Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire video generation process at inference stage. This static conditioning paradigm often creates a mismatch between fixed identity features and dynamically evolving facial motion, leading to identity drift, temporal inconsistency, and degraded perceptual quality. We introduce Test-Time Self-Adaptive Conditioning (TT-SAC), a parameter-free inference framework that "},"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":"2605.25488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T06:45:29Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"514bbc5713679458ef7bd9c5477868db1399fa7217e85e64517abe25778d36f6","abstract_canon_sha256":"0a77d30752d53481d247695e3d7c12c06aa6bf25527bc11b35e9cb18a3281110"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:38.896372Z","signature_b64":"PMRvIR7ANAdBuGEtK/npj6xju6/wDlzzPYwLsChP+nqEJgRRIa9r7GybEIpwM5zNsQkWAdFuHf/tbFf4RmQbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e64cc8c2edea7910996fb91e3d2a4ca3607d951b4e34d35992295a5dc0ec56","last_reissued_at":"2026-05-26T02:04:38.895784Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:38.895784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lei Wang, Yongsheng Gao, Yu Zhang, Zhicheng Zhang","submitted_at":"2026-05-25T06:45:29Z","abstract_excerpt":"Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, most existing approaches rely on a single static reference image to condition the entire video generation process at inference stage. This static conditioning paradigm often creates a mismatch between fixed identity features and dynamically evolving facial motion, leading to identity drift, temporal inconsistency, and degraded perceptual quality. We introduce Test-Time Self-Adaptive Conditioning (TT-SAC), a parameter-free inference framework that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25488","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/2605.25488/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":"2605.25488","created_at":"2026-05-26T02:04:38.895878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25488v1","created_at":"2026-05-26T02:04:38.895878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25488","created_at":"2026-05-26T02:04:38.895878+00:00"},{"alias_kind":"pith_short_12","alias_value":"43TEZSGC5XVH","created_at":"2026-05-26T02:04:38.895878+00:00"},{"alias_kind":"pith_short_16","alias_value":"43TEZSGC5XVHSEEZ","created_at":"2026-05-26T02:04:38.895878+00:00"},{"alias_kind":"pith_short_8","alias_value":"43TEZSGC","created_at":"2026-05-26T02:04:38.895878+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/43TEZSGC5XVHSEEZN64R4PJKJS","json":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS.json","graph_json":"https://pith.science/api/pith-number/43TEZSGC5XVHSEEZN64R4PJKJS/graph.json","events_json":"https://pith.science/api/pith-number/43TEZSGC5XVHSEEZN64R4PJKJS/events.json","paper":"https://pith.science/paper/43TEZSGC"},"agent_actions":{"view_html":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS","download_json":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS.json","view_paper":"https://pith.science/paper/43TEZSGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25488&json=true","fetch_graph":"https://pith.science/api/pith-number/43TEZSGC5XVHSEEZN64R4PJKJS/graph.json","fetch_events":"https://pith.science/api/pith-number/43TEZSGC5XVHSEEZN64R4PJKJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS/action/storage_attestation","attest_author":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS/action/author_attestation","sign_citation":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS/action/citation_signature","submit_replication":"https://pith.science/pith/43TEZSGC5XVHSEEZN64R4PJKJS/action/replication_record"}},"created_at":"2026-05-26T02:04:38.895878+00:00","updated_at":"2026-05-26T02:04:38.895878+00:00"}