{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBEYH4CVKTRMFDCKBVLNTQKUZD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89ce9f457cf2c91b8d6306af07f142ba53e20da6c05abb441fb311b56a936d9d","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T13:58:24Z","title_canon_sha256":"1c5a7a136943f2a5b8385c367a6c9cb16fca5b0898539f59a225a4b5027e5ed9"},"schema_version":"1.0","source":{"id":"2411.17440","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17440","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17440v3","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17440","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"RBEYH4CVKTRM","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"RBEYH4CVKTRMFDCK","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"RBEYH4CV","created_at":"2026-07-05T10:39:23Z"}],"graph_snapshots":[{"event_id":"sha256:c495f012c625c6cba5017098932cd29daf670f8f4e2f31000df6210b99f525d2","target":"graph","created_at":"2026-07-05T10:39:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.17440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving DiT-based control scheme. We propose ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human identity consistent in the generated vi","authors_text":"Jiebo Luo, Jinfa Huang, Liuhan Chen, Li Yuan, Shenghai Yuan, Xianyi He, Yujun Shi, Yunyuan Ge","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T13:58:24Z","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17440","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8246aa369b30d4f319f6369d37b33a5611315f51b4862588c6a5bfb0799b4328","target":"record","created_at":"2026-07-05T10:39:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89ce9f457cf2c91b8d6306af07f142ba53e20da6c05abb441fb311b56a936d9d","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T13:58:24Z","title_canon_sha256":"1c5a7a136943f2a5b8385c367a6c9cb16fca5b0898539f59a225a4b5027e5ed9"},"schema_version":"1.0","source":{"id":"2411.17440","kind":"arxiv","version":3}},"canonical_sha256":"884983f05554e2c28c4a0d56d9c154c8d65f03cd1f91a6bea213664d71f4c002","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"884983f05554e2c28c4a0d56d9c154c8d65f03cd1f91a6bea213664d71f4c002","first_computed_at":"2026-07-05T10:39:23.335146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:23.335146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Y1GOc9K8FORpr0Is1UfosMGUJKoe1ITsVnOkbYlvS5EBdUpehvNh9hnoYCbMEEPwURXpDY79Ae9uphBOS6DBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:23.335647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17440","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8246aa369b30d4f319f6369d37b33a5611315f51b4862588c6a5bfb0799b4328","sha256:c495f012c625c6cba5017098932cd29daf670f8f4e2f31000df6210b99f525d2"],"state_sha256":"45cd948b3768ee96c1364c8443e7e0d847fe4a61790c066cb0fcfa09e4f70103"}