{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65GYNFUGHNFAUKLS7CRGKGJKSC","short_pith_number":"pith:65GYNFUG","schema_version":"1.0","canonical_sha256":"f74d8696863b4a0a2972f8a265192a90948321034e85e46b73dd8b34b3fb4d54","source":{"kind":"arxiv","id":"2408.02629","version":1},"attestation_state":"computed","paper":{"title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Luozheng Qin, Xiaomeng Yang, Zhiyu Tan","submitted_at":"2024-08-05T16:53:23Z","abstract_excerpt":"The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality captions, substandard video quality, and imbalanced data distribution. The prevailing video curation process, which depends on image models for tagging and manual rule-based curation, leads to a high computational load and leaves behind unclean data. As a result, there is a lack of appropriate training datasets for text-to-video models. To address this probl"},"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":"2408.02629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T16:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"2e4c9f644317781a27052337ec7c3ece0d30fd2024ddeca701473753dabf7f20","abstract_canon_sha256":"102b1aca99a4c6fe2d94a1dc871d5d655af6d1da82c4c31d235ff42c86be61e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:15.526172Z","signature_b64":"SJMFLqsnpPLYC03iW5UDTfzLPop0QRYhU6irDwUNsJzS7yPTSuyQfManz4ef0Tj3QwAZ7QVjbTUm1PlC4+fpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74d8696863b4a0a2972f8a265192a90948321034e85e46b73dd8b34b3fb4d54","last_reissued_at":"2026-07-05T08:52:15.525714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:15.525714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Luozheng Qin, Xiaomeng Yang, Zhiyu Tan","submitted_at":"2024-08-05T16:53:23Z","abstract_excerpt":"The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality captions, substandard video quality, and imbalanced data distribution. The prevailing video curation process, which depends on image models for tagging and manual rule-based curation, leads to a high computational load and leaves behind unclean data. As a result, there is a lack of appropriate training datasets for text-to-video models. To address this probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02629","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/2408.02629/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":"2408.02629","created_at":"2026-07-05T08:52:15.525769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02629v1","created_at":"2026-07-05T08:52:15.525769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02629","created_at":"2026-07-05T08:52:15.525769+00:00"},{"alias_kind":"pith_short_12","alias_value":"65GYNFUGHNFA","created_at":"2026-07-05T08:52:15.525769+00:00"},{"alias_kind":"pith_short_16","alias_value":"65GYNFUGHNFAUKLS","created_at":"2026-07-05T08:52:15.525769+00:00"},{"alias_kind":"pith_short_8","alias_value":"65GYNFUG","created_at":"2026-07-05T08:52:15.525769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07534","citing_title":"Infinite Worlds with Versatile Interactions","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2606.16533","citing_title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04737","citing_title":"Physics-Informed Video Generation via Mixture-of-Experts Latent Alignment","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25343","citing_title":"Toward Native Multimodal Modeling: A Roadmap","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01843","citing_title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04068","citing_title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05363","citing_title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04068","citing_title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05539","citing_title":"VDCook:DIY video data cook your MLLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24762","citing_title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07230","citing_title":"PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC","json":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC.json","graph_json":"https://pith.science/api/pith-number/65GYNFUGHNFAUKLS7CRGKGJKSC/graph.json","events_json":"https://pith.science/api/pith-number/65GYNFUGHNFAUKLS7CRGKGJKSC/events.json","paper":"https://pith.science/paper/65GYNFUG"},"agent_actions":{"view_html":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC","download_json":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC.json","view_paper":"https://pith.science/paper/65GYNFUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02629&json=true","fetch_graph":"https://pith.science/api/pith-number/65GYNFUGHNFAUKLS7CRGKGJKSC/graph.json","fetch_events":"https://pith.science/api/pith-number/65GYNFUGHNFAUKLS7CRGKGJKSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC/action/storage_attestation","attest_author":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC/action/author_attestation","sign_citation":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC/action/citation_signature","submit_replication":"https://pith.science/pith/65GYNFUGHNFAUKLS7CRGKGJKSC/action/replication_record"}},"created_at":"2026-07-05T08:52:15.525769+00:00","updated_at":"2026-07-05T08:52:15.525769+00:00"}