{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KAE7LVGKKBLADOTPCFBSPAJURN","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":"5d59a1a161771b1653b4c18060fd29e8f4e944879b83ec686be844f81974359a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:57:49Z","title_canon_sha256":"4ebd409fc3d2906b9ee2be9cabc5e1462321f11679e7b5347294067420313aec"},"schema_version":"1.0","source":{"id":"2410.08260","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08260","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08260v2","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08260","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"KAE7LVGKKBLA","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"KAE7LVGKKBLADOTP","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"KAE7LVGK","created_at":"2026-07-05T10:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:9b68de465b6dc48d67d74a3c23ac208bcc2e444ca6acac0aa4effe7aef966da7","target":"graph","created_at":"2026-07-05T10:54:37Z","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/2410.08260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","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","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:57:49Z","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08260","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":"sha256:11176ac3cec9535c123bedf67a73e6bcc94c95bd2abf3bc460d3ca65f7f68b46","target":"record","created_at":"2026-07-05T10:54:37Z","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":"5d59a1a161771b1653b4c18060fd29e8f4e944879b83ec686be844f81974359a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:57:49Z","title_canon_sha256":"4ebd409fc3d2906b9ee2be9cabc5e1462321f11679e7b5347294067420313aec"},"schema_version":"1.0","source":{"id":"2410.08260","kind":"arxiv","version":2}},"canonical_sha256":"5009f5d4ca505601ba6f11432781348b4165b4740486d36e39777b7b3282a43c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5009f5d4ca505601ba6f11432781348b4165b4740486d36e39777b7b3282a43c","first_computed_at":"2026-07-05T10:54:37.573842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:37.573842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oo6t2XNECN7FxSMT6dLZFunOoTamXSDvf4GvTtTwjbKTyQentj8Vfk8nOApmP6sm7ep9zL5ySMEJkvdu5XUgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:37.574323Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08260","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11176ac3cec9535c123bedf67a73e6bcc94c95bd2abf3bc460d3ca65f7f68b46","sha256:9b68de465b6dc48d67d74a3c23ac208bcc2e444ca6acac0aa4effe7aef966da7"],"state_sha256":"4e06155f5414e844f5f659dde984373de23b2ebb8e1a0910ba0d3182ae660142"}