{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L5MIH5LHMUPUFISNVKULCOJKOA","short_pith_number":"pith:L5MIH5LH","schema_version":"1.0","canonical_sha256":"5f5883f567651f42a24daaa8b1392a7004e8a945e158cec073c5c303dbfed171","source":{"kind":"arxiv","id":"2508.07603","version":1},"attestation_state":"computed","paper":{"title":"LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanhui Li, Jiehui Huang, Long Chen, Panwen Hu, Wenhui Song, Xiaodan Liang, Yiqiang Yan, Yuhao Cheng","submitted_at":"2025-08-11T04:13:32Z","abstract_excerpt":"In this paper, we present LaVieID, a novel \\underline{l}ocal \\underline{a}utoregressive \\underline{vi}d\\underline{e}o diffusion framework designed to tackle the challenging \\underline{id}entity-preserving text-to-video task. The key idea of LaVieID is to mitigate the loss of identity information inherent in the stochastic global generation process of diffusion transformers (DiTs) from both spatial and temporal perspectives. Specifically, unlike the global and unstructured modeling of facial latent states in existing DiTs, LaVieID introduces a local router to explicitly represent latent states "},"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":"2508.07603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T04:13:32Z","cross_cats_sorted":[],"title_canon_sha256":"55ba3668e7a8ec89a31c72ec58700161a29332c8166c4a0597cb861e65e9bf75","abstract_canon_sha256":"f98e1b4b9bf89581ad299bdfce232342ad5fc7389d8cc529be4761e941470d7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:49.103435Z","signature_b64":"z3sARulGMF3WJQLuVRPtVXHI8+2G9v+SfOQ0nUzYOEszPGRpnJElTjZh6h4bqKFzDDaxKrDdFXV9H3Twf+JLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f5883f567651f42a24daaa8b1392a7004e8a945e158cec073c5c303dbfed171","last_reissued_at":"2026-07-05T11:51:49.102955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:49.102955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanhui Li, Jiehui Huang, Long Chen, Panwen Hu, Wenhui Song, Xiaodan Liang, Yiqiang Yan, Yuhao Cheng","submitted_at":"2025-08-11T04:13:32Z","abstract_excerpt":"In this paper, we present LaVieID, a novel \\underline{l}ocal \\underline{a}utoregressive \\underline{vi}d\\underline{e}o diffusion framework designed to tackle the challenging \\underline{id}entity-preserving text-to-video task. The key idea of LaVieID is to mitigate the loss of identity information inherent in the stochastic global generation process of diffusion transformers (DiTs) from both spatial and temporal perspectives. Specifically, unlike the global and unstructured modeling of facial latent states in existing DiTs, LaVieID introduces a local router to explicitly represent latent states "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07603","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/2508.07603/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":"2508.07603","created_at":"2026-07-05T11:51:49.103011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07603v1","created_at":"2026-07-05T11:51:49.103011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07603","created_at":"2026-07-05T11:51:49.103011+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5MIH5LHMUPU","created_at":"2026-07-05T11:51:49.103011+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5MIH5LHMUPUFISN","created_at":"2026-07-05T11:51:49.103011+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5MIH5LH","created_at":"2026-07-05T11:51:49.103011+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/L5MIH5LHMUPUFISNVKULCOJKOA","json":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA.json","graph_json":"https://pith.science/api/pith-number/L5MIH5LHMUPUFISNVKULCOJKOA/graph.json","events_json":"https://pith.science/api/pith-number/L5MIH5LHMUPUFISNVKULCOJKOA/events.json","paper":"https://pith.science/paper/L5MIH5LH"},"agent_actions":{"view_html":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA","download_json":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA.json","view_paper":"https://pith.science/paper/L5MIH5LH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07603&json=true","fetch_graph":"https://pith.science/api/pith-number/L5MIH5LHMUPUFISNVKULCOJKOA/graph.json","fetch_events":"https://pith.science/api/pith-number/L5MIH5LHMUPUFISNVKULCOJKOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA/action/storage_attestation","attest_author":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA/action/author_attestation","sign_citation":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA/action/citation_signature","submit_replication":"https://pith.science/pith/L5MIH5LHMUPUFISNVKULCOJKOA/action/replication_record"}},"created_at":"2026-07-05T11:51:49.103011+00:00","updated_at":"2026-07-05T11:51:49.103011+00:00"}