{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CC6VPKJBRMSMLPHOZL63JHBJ3P","short_pith_number":"pith:CC6VPKJB","schema_version":"1.0","canonical_sha256":"10bd57a9218b24c5bceecafdb49c29dbe388e4e89d82466a4aec793f8383eb53","source":{"kind":"arxiv","id":"2412.15646","version":2},"attestation_state":"computed","paper":{"title":"CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Bo Liu, Jian Lu, Weisheng Li, Xiaodong Cun, Xiuli Bi, Yong Zhang","submitted_at":"2024-12-20T08:05:13Z","abstract_excerpt":"Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, given some reference images or videos, the parameter-efficient fine-tuning method, i.e. LoRA, can generate high-quality customized concepts, e.g., the specific subject or the motions from a reference video. However, combining the trained multiple concepts from different references into a single network shows obvious artifacts. To this end, we propose CustomTTT, where we can joint custom the appearance and the motion of t"},"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":"2412.15646","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T08:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"a8d3c147c930cd6dbfc82966fe44f14ec1bd0c7794edad3764a6e6afc368c71d","abstract_canon_sha256":"1d89179b7c2a672e3157f0a08b73ebe9d31969353c9d1d18b72fb04c6471ac73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:09.722838Z","signature_b64":"d2o25E19FUsw+ISTqEBJvRwjMGXZAgIwQtb7V1qTvYgBiPzd7Gdui5HGmyJHWyByAmPj8Uy/tvrgYGFhtD/2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10bd57a9218b24c5bceecafdb49c29dbe388e4e89d82466a4aec793f8383eb53","last_reissued_at":"2026-07-05T09:53:09.722351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:09.722351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Bo Liu, Jian Lu, Weisheng Li, Xiaodong Cun, Xiuli Bi, Yong Zhang","submitted_at":"2024-12-20T08:05:13Z","abstract_excerpt":"Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, given some reference images or videos, the parameter-efficient fine-tuning method, i.e. LoRA, can generate high-quality customized concepts, e.g., the specific subject or the motions from a reference video. However, combining the trained multiple concepts from different references into a single network shows obvious artifacts. To this end, we propose CustomTTT, where we can joint custom the appearance and the motion of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15646","kind":"arxiv","version":2},"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/2412.15646/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":"2412.15646","created_at":"2026-07-05T09:53:09.722410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15646v2","created_at":"2026-07-05T09:53:09.722410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15646","created_at":"2026-07-05T09:53:09.722410+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC6VPKJBRMSM","created_at":"2026-07-05T09:53:09.722410+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC6VPKJBRMSMLPHO","created_at":"2026-07-05T09:53:09.722410+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC6VPKJB","created_at":"2026-07-05T09:53:09.722410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P","json":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P.json","graph_json":"https://pith.science/api/pith-number/CC6VPKJBRMSMLPHOZL63JHBJ3P/graph.json","events_json":"https://pith.science/api/pith-number/CC6VPKJBRMSMLPHOZL63JHBJ3P/events.json","paper":"https://pith.science/paper/CC6VPKJB"},"agent_actions":{"view_html":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P","download_json":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P.json","view_paper":"https://pith.science/paper/CC6VPKJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15646&json=true","fetch_graph":"https://pith.science/api/pith-number/CC6VPKJBRMSMLPHOZL63JHBJ3P/graph.json","fetch_events":"https://pith.science/api/pith-number/CC6VPKJBRMSMLPHOZL63JHBJ3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P/action/storage_attestation","attest_author":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P/action/author_attestation","sign_citation":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P/action/citation_signature","submit_replication":"https://pith.science/pith/CC6VPKJBRMSMLPHOZL63JHBJ3P/action/replication_record"}},"created_at":"2026-07-05T09:53:09.722410+00:00","updated_at":"2026-07-05T09:53:09.722410+00:00"}