{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQFXZEM7ODQFIMDTNP7AFARSUC","short_pith_number":"pith:MQFXZEM7","schema_version":"1.0","canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","source":{"kind":"arxiv","id":"2412.18597","version":2},"attestation_state":"computed","paper":{"title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Minghong Cai, Wenze Liu, Xiangyu Yue, Xiaodong Cun, Xiaoyu Li, Ying Shan, Yong Zhang, Zhaoyang Zhang","submitted_at":"2024-12-24T18:51:19Z","abstract_excerpt":"Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate coherent scenes with multiple sequential prompts that better reflect real-world dynamic scenarios. While some pioneering works have explored multi-prompt video generation, they face significant challenges including strict training data requirements, weak prompt following, and unnatural transitions. To address these problems, we propose DiTCtrl, a training-free m"},"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":"2412.18597","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:51:19Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"05934ea1bd30a918b67e830075a941678a6885bbd432a956b2da109c985fd81f","abstract_canon_sha256":"9001594f36b5a00ed996bab7a79130160b3a2fc0507a4d8b97f320322dd2b368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:24.756039Z","signature_b64":"QFcuRIN+9VDOE3oti7qZQaCOqeRElsLVCHJaaimEcXAdc8b4INoCiZ7xlH/1KeGHMF6OWZcp5LugpjeHn3o+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","last_reissued_at":"2026-07-05T10:39:24.755561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:24.755561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Minghong Cai, Wenze Liu, Xiangyu Yue, Xiaodong Cun, Xiaoyu Li, Ying Shan, Yong Zhang, Zhaoyang Zhang","submitted_at":"2024-12-24T18:51:19Z","abstract_excerpt":"Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate coherent scenes with multiple sequential prompts that better reflect real-world dynamic scenarios. While some pioneering works have explored multi-prompt video generation, they face significant challenges including strict training data requirements, weak prompt following, and unnatural transitions. To address these problems, we propose DiTCtrl, a training-free m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18597","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/2412.18597/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":"2412.18597","created_at":"2026-07-05T10:39:24.755619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18597v2","created_at":"2026-07-05T10:39:24.755619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18597","created_at":"2026-07-05T10:39:24.755619+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQFXZEM7ODQF","created_at":"2026-07-05T10:39:24.755619+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQFXZEM7ODQFIMDT","created_at":"2026-07-05T10:39:24.755619+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQFXZEM7","created_at":"2026-07-05T10:39:24.755619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22996","citing_title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC","json":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC.json","graph_json":"https://pith.science/api/pith-number/MQFXZEM7ODQFIMDTNP7AFARSUC/graph.json","events_json":"https://pith.science/api/pith-number/MQFXZEM7ODQFIMDTNP7AFARSUC/events.json","paper":"https://pith.science/paper/MQFXZEM7"},"agent_actions":{"view_html":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC","download_json":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC.json","view_paper":"https://pith.science/paper/MQFXZEM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18597&json=true","fetch_graph":"https://pith.science/api/pith-number/MQFXZEM7ODQFIMDTNP7AFARSUC/graph.json","fetch_events":"https://pith.science/api/pith-number/MQFXZEM7ODQFIMDTNP7AFARSUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/action/storage_attestation","attest_author":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/action/author_attestation","sign_citation":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/action/citation_signature","submit_replication":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/action/replication_record"}},"created_at":"2026-07-05T10:39:24.755619+00:00","updated_at":"2026-07-05T10:39:24.755619+00:00"}