{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3I7PCH6HTSYNCCJWJYQ3XURT7A","short_pith_number":"pith:3I7PCH6H","schema_version":"1.0","canonical_sha256":"da3ef11fc79cb0d109364e21bbd233f829fbdb0518ffb474aff07dc9cde2a321","source":{"kind":"arxiv","id":"2305.18264","version":1},"attestation_state":"computed","paper":{"title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu-Yun Wang, Guanglu Song, Han-Jia Ye, Hongsheng Li, Wenshuo Chen, Yu Liu","submitted_at":"2023-05-29T17:38:18Z","abstract_excerpt":"Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically less than 24 frames) and are limited to a single text condition. These constraints significantly limit their applications given that real-world "},"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":"2305.18264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"0c3ffe27f1be75ab2c4c161309ad734bdb707b32ed22c3abd8ecf6ade882d04b","abstract_canon_sha256":"4ca3d4111a36c8817e3cd0ac2def0296d186f8d4542b33df82e0e811ca92c881"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:54.154310Z","signature_b64":"1RZ7cI26LjJO9iXadtHybzoYxUaSMY+uLAMr4xJtw4v7p9jGq9eNFCSkhUhZeHH2JIdgDtHNPiBAdxHWqBuJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3ef11fc79cb0d109364e21bbd233f829fbdb0518ffb474aff07dc9cde2a321","last_reissued_at":"2026-07-05T06:14:54.153810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:54.153810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu-Yun Wang, Guanglu Song, Han-Jia Ye, Hongsheng Li, Wenshuo Chen, Yu Liu","submitted_at":"2023-05-29T17:38:18Z","abstract_excerpt":"Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically less than 24 frames) and are limited to a single text condition. These constraints significantly limit their applications given that real-world "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18264","kind":"arxiv","version":1},"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/2305.18264/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":"2305.18264","created_at":"2026-07-05T06:14:54.153868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18264v1","created_at":"2026-07-05T06:14:54.153868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18264","created_at":"2026-07-05T06:14:54.153868+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I7PCH6HTSYN","created_at":"2026-07-05T06:14:54.153868+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I7PCH6HTSYNCCJW","created_at":"2026-07-05T06:14:54.153868+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I7PCH6H","created_at":"2026-07-05T06:14:54.153868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10543","citing_title":"TIE: Time Interval Encoding for Video Generation over Events","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31590","citing_title":"TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00837","citing_title":"Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00793","citing_title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23508","citing_title":"DrawVideo: Generating Long Video from Storyboard Keyframe Sketches","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06310","citing_title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":25,"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":78,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19325","citing_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10543","citing_title":"TIE: Time Interval Encoding for Video Generation over Events","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06512","citing_title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06509","citing_title":"FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A","json":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A.json","graph_json":"https://pith.science/api/pith-number/3I7PCH6HTSYNCCJWJYQ3XURT7A/graph.json","events_json":"https://pith.science/api/pith-number/3I7PCH6HTSYNCCJWJYQ3XURT7A/events.json","paper":"https://pith.science/paper/3I7PCH6H"},"agent_actions":{"view_html":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A","download_json":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A.json","view_paper":"https://pith.science/paper/3I7PCH6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18264&json=true","fetch_graph":"https://pith.science/api/pith-number/3I7PCH6HTSYNCCJWJYQ3XURT7A/graph.json","fetch_events":"https://pith.science/api/pith-number/3I7PCH6HTSYNCCJWJYQ3XURT7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A/action/storage_attestation","attest_author":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A/action/author_attestation","sign_citation":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A/action/citation_signature","submit_replication":"https://pith.science/pith/3I7PCH6HTSYNCCJWJYQ3XURT7A/action/replication_record"}},"created_at":"2026-07-05T06:14:54.153868+00:00","updated_at":"2026-07-05T06:14:54.153868+00:00"}