{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MQFXZEM7ODQFIMDTNP7AFARSUC","short_pith_number":"pith:MQFXZEM7","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"},"canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","source":{"kind":"arxiv","id":"2412.18597","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18597","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18597v2","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18597","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"MQFXZEM7ODQF","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"MQFXZEM7ODQFIMDT","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"MQFXZEM7","created_at":"2026-07-05T10:39:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MQFXZEM7ODQFIMDTNP7AFARSUC","target":"record","payload":{"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"},"canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","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"},"source_kind":"arxiv","source_id":"2412.18597","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a8Z5BZLyau7VR5jigm4ywYCuJ1YTg/JidHFjDhBKSqTgaJ3DW7Bgv0nHbB9d7cdUwEBLz+8TEiiiMMeeUdGMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:55:59.321661Z"},"content_sha256":"e01483716a8df5fe187ca26831019ebb83b82f08e1f38b117581f5d1dca431bb","schema_version":"1.0","event_id":"sha256:e01483716a8df5fe187ca26831019ebb83b82f08e1f38b117581f5d1dca431bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MQFXZEM7ODQFIMDTNP7AFARSUC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ndQWPpd1VX57t9Dv4vTUt1zj3YIi60W1PO5bhQIirJGMueLq3gtuofvjgkJ/IswOMB7x5ES4S4Xl4ys9i46nDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:55:59.322585Z"},"content_sha256":"bcb627db263d751fd9a424ed9b8139cdf88e194195f91a155ea9ad7fa547fe41","schema_version":"1.0","event_id":"sha256:bcb627db263d751fd9a424ed9b8139cdf88e194195f91a155ea9ad7fa547fe41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/bundle.json","state_url":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T15:55:59Z","links":{"resolver":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC","bundle":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/bundle.json","state":"https://pith.science/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQFXZEM7ODQFIMDTNP7AFARSUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MQFXZEM7ODQFIMDTNP7AFARSUC","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":"9001594f36b5a00ed996bab7a79130160b3a2fc0507a4d8b97f320322dd2b368","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:51:19Z","title_canon_sha256":"05934ea1bd30a918b67e830075a941678a6885bbd432a956b2da109c985fd81f"},"schema_version":"1.0","source":{"id":"2412.18597","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18597","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18597v2","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18597","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"MQFXZEM7ODQF","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"MQFXZEM7ODQFIMDT","created_at":"2026-07-05T10:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"MQFXZEM7","created_at":"2026-07-05T10:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:bcb627db263d751fd9a424ed9b8139cdf88e194195f91a155ea9ad7fa547fe41","target":"graph","created_at":"2026-07-05T10:39:24Z","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/2412.18597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Minghong Cai, Wenze Liu, Xiangyu Yue, Xiaodong Cun, Xiaoyu Li, Ying Shan, Yong Zhang, Zhaoyang Zhang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:51:19Z","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18597","kind":"arxiv","version":2},"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:e01483716a8df5fe187ca26831019ebb83b82f08e1f38b117581f5d1dca431bb","target":"record","created_at":"2026-07-05T10:39:24Z","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":"9001594f36b5a00ed996bab7a79130160b3a2fc0507a4d8b97f320322dd2b368","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:51:19Z","title_canon_sha256":"05934ea1bd30a918b67e830075a941678a6885bbd432a956b2da109c985fd81f"},"schema_version":"1.0","source":{"id":"2412.18597","kind":"arxiv","version":2}},"canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"640b7c919f70e05430736bfe028232a08a6b7ca29b1669fadeda9502f744c89f","first_computed_at":"2026-07-05T10:39:24.755561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:24.755561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QFcuRIN+9VDOE3oti7qZQaCOqeRElsLVCHJaaimEcXAdc8b4INoCiZ7xlH/1KeGHMF6OWZcp5LugpjeHn3o+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:24.756039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18597","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e01483716a8df5fe187ca26831019ebb83b82f08e1f38b117581f5d1dca431bb","sha256:bcb627db263d751fd9a424ed9b8139cdf88e194195f91a155ea9ad7fa547fe41"],"state_sha256":"c896bf49ed0b7cc5b762bbb4dc9fd272e2dc8d0b66b950aa094f28ffec7b2395"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5slYj+YBUg4IQ28JuRAyKIbkoftYQEo4cWZ4fgWgOsNVsI/DRKZg1ByfwQV3WpYWvX+P/8eJe/OqFW78gOXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:55:59.328501Z","bundle_sha256":"e44477fb820ef35bd23d6b3131f7c606b05733cbcced629b0d967186fe22169e"}}