{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V57Q5J4PT4PLUHQ3LM6DW2TPK7","short_pith_number":"pith:V57Q5J4P","schema_version":"1.0","canonical_sha256":"af7f0ea78f9f1eba1e1b5b3c3b6a6f57c43ec048fedb8e92c3dd4ac55ee9268b","source":{"kind":"arxiv","id":"2508.06511","version":1},"attestation_state":"computed","paper":{"title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglin Di, He Feng, Lei Fan, Tonghua Su, Xiangqian Wu, Yongjia Ma","submitted_at":"2025-07-29T08:23:56Z","abstract_excerpt":"Portrait animation aims to synthesize talking videos from a static reference face, conditioned on audio and style frame cues (e.g., emotion and head poses), while ensuring precise lip synchronization and faithful reproduction of speaking styles. Existing diffusion-based portrait animation methods primarily focus on lip synchronization or static emotion transformation, often overlooking dynamic styles such as head movements. Moreover, most of these methods rely on a dual U-Net architecture, which preserves identity consistency but incurs additional computational overhead. To this end, we propos"},"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":"2508.06511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T08:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"41ff06e98b1db7fde53e2fbdb671be9f63be436382a6269946f255227776c112","abstract_canon_sha256":"f1adeebcf565f714267bbdbafecd86caf752a9a93b48d17b36b96a56c5e9dae4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:00.922990Z","signature_b64":"tKYkjX+IXXSz90LB7SYdt6Sjv9R3GzG8e3EKd8cSlhlGCXAXQW16MXVNktQSsFNxGdA90ki91bf9wrNp+CEbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7f0ea78f9f1eba1e1b5b3c3b6a6f57c43ec048fedb8e92c3dd4ac55ee9268b","last_reissued_at":"2026-07-05T11:51:00.922443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:00.922443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donglin Di, He Feng, Lei Fan, Tonghua Su, Xiangqian Wu, Yongjia Ma","submitted_at":"2025-07-29T08:23:56Z","abstract_excerpt":"Portrait animation aims to synthesize talking videos from a static reference face, conditioned on audio and style frame cues (e.g., emotion and head poses), while ensuring precise lip synchronization and faithful reproduction of speaking styles. Existing diffusion-based portrait animation methods primarily focus on lip synchronization or static emotion transformation, often overlooking dynamic styles such as head movements. Moreover, most of these methods rely on a dual U-Net architecture, which preserves identity consistency but incurs additional computational overhead. To this end, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06511","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/2508.06511/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":"2508.06511","created_at":"2026-07-05T11:51:00.922505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06511v1","created_at":"2026-07-05T11:51:00.922505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06511","created_at":"2026-07-05T11:51:00.922505+00:00"},{"alias_kind":"pith_short_12","alias_value":"V57Q5J4PT4PL","created_at":"2026-07-05T11:51:00.922505+00:00"},{"alias_kind":"pith_short_16","alias_value":"V57Q5J4PT4PLUHQ3","created_at":"2026-07-05T11:51:00.922505+00:00"},{"alias_kind":"pith_short_8","alias_value":"V57Q5J4P","created_at":"2026-07-05T11:51:00.922505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28056","citing_title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7","json":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7.json","graph_json":"https://pith.science/api/pith-number/V57Q5J4PT4PLUHQ3LM6DW2TPK7/graph.json","events_json":"https://pith.science/api/pith-number/V57Q5J4PT4PLUHQ3LM6DW2TPK7/events.json","paper":"https://pith.science/paper/V57Q5J4P"},"agent_actions":{"view_html":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7","download_json":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7.json","view_paper":"https://pith.science/paper/V57Q5J4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06511&json=true","fetch_graph":"https://pith.science/api/pith-number/V57Q5J4PT4PLUHQ3LM6DW2TPK7/graph.json","fetch_events":"https://pith.science/api/pith-number/V57Q5J4PT4PLUHQ3LM6DW2TPK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7/action/storage_attestation","attest_author":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7/action/author_attestation","sign_citation":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7/action/citation_signature","submit_replication":"https://pith.science/pith/V57Q5J4PT4PLUHQ3LM6DW2TPK7/action/replication_record"}},"created_at":"2026-07-05T11:51:00.922505+00:00","updated_at":"2026-07-05T11:51:00.922505+00:00"}