{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U7AAAVJEZX7HJHODCTDKXU4JK6","short_pith_number":"pith:U7AAAVJE","schema_version":"1.0","canonical_sha256":"a7c0005524cdfe749dc314c6abd3895795dfefdab3e46ed0b7972b78ef5ffdb6","source":{"kind":"arxiv","id":"2508.11255","version":1},"attestation_state":"computed","paper":{"title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jiang, Mengchao Wang, Mu Xu, Qiang Wang","submitted_at":"2025-08-15T06:43:46Z","abstract_excerpt":"Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync accuracy, and visual quality. This is due to the difficulty of optimizing among competing preference objectives, which often conflict with one another, and the scarcity of large-scale, high-quality datasets with multidimensional preference annotations. To address these, we first introduce Talking-Critic, a multimodal reward model that learns human-aligned rew"},"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":"2508.11255","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T06:43:46Z","cross_cats_sorted":[],"title_canon_sha256":"91ed21bd8f75624e1d7b687a29950e87d744d78ef90cd7b732bf4be7cff146d9","abstract_canon_sha256":"dca39cb60aef7176a3b3fb57001b5c7a2cc8e7831b73cd53d8da9de18f32afd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:21.498383Z","signature_b64":"MCgNtMH/aPF6jVD47krPqMV1k339GgFCOzBbkxf3f7R0pc1PnYN541K3LRWUHTbDJh/d7wR00ypF1zjk2c+ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c0005524cdfe749dc314c6abd3895795dfefdab3e46ed0b7972b78ef5ffdb6","last_reissued_at":"2026-07-05T11:54:21.497781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:21.497781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jiang, Mengchao Wang, Mu Xu, Qiang Wang","submitted_at":"2025-08-15T06:43:46Z","abstract_excerpt":"Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync accuracy, and visual quality. This is due to the difficulty of optimizing among competing preference objectives, which often conflict with one another, and the scarcity of large-scale, high-quality datasets with multidimensional preference annotations. To address these, we first introduce Talking-Critic, a multimodal reward model that learns human-aligned rew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11255","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/2508.11255/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":"2508.11255","created_at":"2026-07-05T11:54:21.497845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11255v1","created_at":"2026-07-05T11:54:21.497845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11255","created_at":"2026-07-05T11:54:21.497845+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7AAAVJEZX7H","created_at":"2026-07-05T11:54:21.497845+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7AAAVJEZX7HJHOD","created_at":"2026-07-05T11:54:21.497845+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7AAAVJE","created_at":"2026-07-05T11:54:21.497845+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/U7AAAVJEZX7HJHODCTDKXU4JK6","json":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6.json","graph_json":"https://pith.science/api/pith-number/U7AAAVJEZX7HJHODCTDKXU4JK6/graph.json","events_json":"https://pith.science/api/pith-number/U7AAAVJEZX7HJHODCTDKXU4JK6/events.json","paper":"https://pith.science/paper/U7AAAVJE"},"agent_actions":{"view_html":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6","download_json":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6.json","view_paper":"https://pith.science/paper/U7AAAVJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11255&json=true","fetch_graph":"https://pith.science/api/pith-number/U7AAAVJEZX7HJHODCTDKXU4JK6/graph.json","fetch_events":"https://pith.science/api/pith-number/U7AAAVJEZX7HJHODCTDKXU4JK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6/action/storage_attestation","attest_author":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6/action/author_attestation","sign_citation":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6/action/citation_signature","submit_replication":"https://pith.science/pith/U7AAAVJEZX7HJHODCTDKXU4JK6/action/replication_record"}},"created_at":"2026-07-05T11:54:21.497845+00:00","updated_at":"2026-07-05T11:54:21.497845+00:00"}