{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KAE7LVGKKBLADOTPCFBSPAJURN","short_pith_number":"pith:KAE7LVGK","schema_version":"1.0","canonical_sha256":"5009f5d4ca505601ba6f11432781348b4165b4740486d36e39777b7b3282a43c","source":{"kind":"arxiv","id":"2410.08260","version":2},"attestation_state":"computed","paper":{"title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyuan Jiang, Di Zhang, Fei Yang, Haotian Yang, Jiahao Wang, Jiarong Ou, Ke Lin, Mingwu Zheng, Pengfei Wan, Qiuheng Wang, Rui Chen, Xin Tao, Yukai Shi","submitted_at":"2024-10-10T17:57:49Z","abstract_excerpt":"With the continuous progress of visual generation technologies, the scale of video datasets has grown exponentially. The quality of these datasets plays a pivotal role in the performance of video generation models. We assert that temporal splitting, detailed captions, and video quality filtering are three crucial determinants of dataset quality. However, existing datasets exhibit various limitations in these areas. To address these challenges, we introduce Koala-36M, a large-scale, high-quality video dataset featuring accurate temporal splitting, detailed captions, and superior video quality. "},"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":"2410.08260","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:57:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ebd409fc3d2906b9ee2be9cabc5e1462321f11679e7b5347294067420313aec","abstract_canon_sha256":"5d59a1a161771b1653b4c18060fd29e8f4e944879b83ec686be844f81974359a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:37.574323Z","signature_b64":"Oo6t2XNECN7FxSMT6dLZFunOoTamXSDvf4GvTtTwjbKTyQentj8Vfk8nOApmP6sm7ep9zL5ySMEJkvdu5XUgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5009f5d4ca505601ba6f11432781348b4165b4740486d36e39777b7b3282a43c","last_reissued_at":"2026-07-05T10:54:37.573842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:37.573842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyuan Jiang, Di Zhang, Fei Yang, Haotian Yang, Jiahao Wang, Jiarong Ou, Ke Lin, Mingwu Zheng, Pengfei Wan, Qiuheng Wang, Rui Chen, Xin Tao, Yukai Shi","submitted_at":"2024-10-10T17:57:49Z","abstract_excerpt":"With the continuous progress of visual generation technologies, the scale of video datasets has grown exponentially. The quality of these datasets plays a pivotal role in the performance of video generation models. We assert that temporal splitting, detailed captions, and video quality filtering are three crucial determinants of dataset quality. However, existing datasets exhibit various limitations in these areas. To address these challenges, we introduce Koala-36M, a large-scale, high-quality video dataset featuring accurate temporal splitting, detailed captions, and superior video quality. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08260","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/2410.08260/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":"2410.08260","created_at":"2026-07-05T10:54:37.573912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08260v2","created_at":"2026-07-05T10:54:37.573912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08260","created_at":"2026-07-05T10:54:37.573912+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAE7LVGKKBLA","created_at":"2026-07-05T10:54:37.573912+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAE7LVGKKBLADOTP","created_at":"2026-07-05T10:54:37.573912+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAE7LVGK","created_at":"2026-07-05T10:54:37.573912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16503","citing_title":"Motif-Video 2B: Technical Report","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16503","citing_title":"Motif-Video 2B: Technical Report","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN","json":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN.json","graph_json":"https://pith.science/api/pith-number/KAE7LVGKKBLADOTPCFBSPAJURN/graph.json","events_json":"https://pith.science/api/pith-number/KAE7LVGKKBLADOTPCFBSPAJURN/events.json","paper":"https://pith.science/paper/KAE7LVGK"},"agent_actions":{"view_html":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN","download_json":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN.json","view_paper":"https://pith.science/paper/KAE7LVGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08260&json=true","fetch_graph":"https://pith.science/api/pith-number/KAE7LVGKKBLADOTPCFBSPAJURN/graph.json","fetch_events":"https://pith.science/api/pith-number/KAE7LVGKKBLADOTPCFBSPAJURN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN/action/storage_attestation","attest_author":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN/action/author_attestation","sign_citation":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN/action/citation_signature","submit_replication":"https://pith.science/pith/KAE7LVGKKBLADOTPCFBSPAJURN/action/replication_record"}},"created_at":"2026-07-05T10:54:37.573912+00:00","updated_at":"2026-07-05T10:54:37.573912+00:00"}