{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XHP47XEWXDSHJH3V7BB32UKM23","short_pith_number":"pith:XHP47XEW","schema_version":"1.0","canonical_sha256":"b9dfcfdc96b8e4749f75f843bd514cd6c985ae76f71ea4585c53e2ab809aeae2","source":{"kind":"arxiv","id":"2310.15169","version":3},"attestation_state":"computed","paper":{"title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Qiu, Menghan Xia, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang, Ziwei Liu","submitted_at":"2023-10-23T17:59:58Z","abstract_excerpt":"With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference. Furthermore, these models only support single-text conditions, whereas real-life scenarios often require multi-text conditions as the video content changes over time. To tackle these challenges, this study explores the potential of extending the text-driven capability"},"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":"2310.15169","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"450635fcdcb97c1f2fe2ed5d04f7323f54d9be93a72932ca74166720936cb60e","abstract_canon_sha256":"86c86ab1f4a64be2feca08448fb1c5a92f16b0e9b0343dd1d2c84a18f65df88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:11.535465Z","signature_b64":"lB2pWjDLYEzFp2l0JhoWDnTMMm7aTHWD642i3gA5HWkOe3CUX+2B2Qf69230ZqGtzNmXg/i7ObWsfETCtB+gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9dfcfdc96b8e4749f75f843bd514cd6c985ae76f71ea4585c53e2ab809aeae2","last_reissued_at":"2026-07-05T07:39:11.535051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:11.535051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Qiu, Menghan Xia, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang, Ziwei Liu","submitted_at":"2023-10-23T17:59:58Z","abstract_excerpt":"With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference. Furthermore, these models only support single-text conditions, whereas real-life scenarios often require multi-text conditions as the video content changes over time. To tackle these challenges, this study explores the potential of extending the text-driven capability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15169","kind":"arxiv","version":3},"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/2310.15169/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":"2310.15169","created_at":"2026-07-05T07:39:11.535101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15169v3","created_at":"2026-07-05T07:39:11.535101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15169","created_at":"2026-07-05T07:39:11.535101+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHP47XEWXDSH","created_at":"2026-07-05T07:39:11.535101+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHP47XEWXDSHJH3V","created_at":"2026-07-05T07:39:11.535101+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHP47XEW","created_at":"2026-07-05T07:39:11.535101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08770","citing_title":"LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.16449","citing_title":"PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02517","citing_title":"WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02436","citing_title":"Geometry-Aware Implicit Memory for Video World Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00793","citing_title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06310","citing_title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":210,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13009","citing_title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04678","citing_title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06512","citing_title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23","json":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23.json","graph_json":"https://pith.science/api/pith-number/XHP47XEWXDSHJH3V7BB32UKM23/graph.json","events_json":"https://pith.science/api/pith-number/XHP47XEWXDSHJH3V7BB32UKM23/events.json","paper":"https://pith.science/paper/XHP47XEW"},"agent_actions":{"view_html":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23","download_json":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23.json","view_paper":"https://pith.science/paper/XHP47XEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15169&json=true","fetch_graph":"https://pith.science/api/pith-number/XHP47XEWXDSHJH3V7BB32UKM23/graph.json","fetch_events":"https://pith.science/api/pith-number/XHP47XEWXDSHJH3V7BB32UKM23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23/action/storage_attestation","attest_author":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23/action/author_attestation","sign_citation":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23/action/citation_signature","submit_replication":"https://pith.science/pith/XHP47XEWXDSHJH3V7BB32UKM23/action/replication_record"}},"created_at":"2026-07-05T07:39:11.535101+00:00","updated_at":"2026-07-05T07:39:11.535101+00:00"}