{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GEUEKERHAE4CJXSTQDKGIJ5EL4","short_pith_number":"pith:GEUEKERH","schema_version":"1.0","canonical_sha256":"3128451227013824de5380d46427a45f2ec5e0c96838594008d121a026ce4c56","source":{"kind":"arxiv","id":"2411.17470","version":2},"attestation_state":"computed","paper":{"title":"Towards Precise Scaling Laws for Video Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoqun Yin, Di Zhang, Jiahao Wang, Jiarong Ou, Ke Lin, Kun Gai, Mingwu Zheng, Pengfei Wan, Rui Chen, Victor Shea-Jay Huang, Wentao Zhang, Xin Tao, Yaqi Zhao, Yuanyang Yin","submitted_at":"2024-11-25T18:59:04Z","abstract_excerpt":"Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-scale training. While scaling laws are employed in language models to predict performance, their existence and accurate derivation in visual generation models remain underexplored. In this paper, we systematically analyze scaling laws for video diffusion transformers and confirm their presence. Moreover, we discover that, unlike language models, vid"},"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":"2411.17470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:59:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"96ded597cd3ea005d5a7ded74b88316a0ed680499242398f4ee5457f7329e271","abstract_canon_sha256":"7dca91874cc4ae53dee0197e707bbb2b06a2d6027419f019130afc70a6f33bc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:02.677747Z","signature_b64":"MNHxs1/zKOwrm/nimG213eeB3Xv+5y3kgzSOzxGnBpKSX9YYjRmetVUlAxhtKKzUnBLqfD2BY0wVffdMAHaGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3128451227013824de5380d46427a45f2ec5e0c96838594008d121a026ce4c56","last_reissued_at":"2026-07-05T09:56:02.677259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:02.677259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Precise Scaling Laws for Video Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoqun Yin, Di Zhang, Jiahao Wang, Jiarong Ou, Ke Lin, Kun Gai, Mingwu Zheng, Pengfei Wan, Rui Chen, Victor Shea-Jay Huang, Wentao Zhang, Xin Tao, Yaqi Zhao, Yuanyang Yin","submitted_at":"2024-11-25T18:59:04Z","abstract_excerpt":"Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-scale training. While scaling laws are employed in language models to predict performance, their existence and accurate derivation in visual generation models remain underexplored. In this paper, we systematically analyze scaling laws for video diffusion transformers and confirm their presence. Moreover, we discover that, unlike language models, vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17470","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/2411.17470/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":"2411.17470","created_at":"2026-07-05T09:56:02.677325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17470v2","created_at":"2026-07-05T09:56:02.677325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17470","created_at":"2026-07-05T09:56:02.677325+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEUEKERHAE4C","created_at":"2026-07-05T09:56:02.677325+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEUEKERHAE4CJXST","created_at":"2026-07-05T09:56:02.677325+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEUEKERH","created_at":"2026-07-05T09:56:02.677325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4","json":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4.json","graph_json":"https://pith.science/api/pith-number/GEUEKERHAE4CJXSTQDKGIJ5EL4/graph.json","events_json":"https://pith.science/api/pith-number/GEUEKERHAE4CJXSTQDKGIJ5EL4/events.json","paper":"https://pith.science/paper/GEUEKERH"},"agent_actions":{"view_html":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4","download_json":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4.json","view_paper":"https://pith.science/paper/GEUEKERH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17470&json=true","fetch_graph":"https://pith.science/api/pith-number/GEUEKERHAE4CJXSTQDKGIJ5EL4/graph.json","fetch_events":"https://pith.science/api/pith-number/GEUEKERHAE4CJXSTQDKGIJ5EL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4/action/storage_attestation","attest_author":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4/action/author_attestation","sign_citation":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4/action/citation_signature","submit_replication":"https://pith.science/pith/GEUEKERHAE4CJXSTQDKGIJ5EL4/action/replication_record"}},"created_at":"2026-07-05T09:56:02.677325+00:00","updated_at":"2026-07-05T09:56:02.677325+00:00"}