{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U7WRXIV77CDCMQGVX4PCXN3BFF","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":"6bfbb91612903815b1a00a889e065180c874a87046aef7c1c432fd4b2db9f068","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T14:28:41Z","title_canon_sha256":"23f44789a816106431635bc5bd0b52a7c11b111ec61d24c672dd50f3481378c1"},"schema_version":"1.0","source":{"id":"2303.16727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16727","created_at":"2026-07-05T06:02:08Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16727v2","created_at":"2026-07-05T06:02:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16727","created_at":"2026-07-05T06:02:08Z"},{"alias_kind":"pith_short_12","alias_value":"U7WRXIV77CDC","created_at":"2026-07-05T06:02:08Z"},{"alias_kind":"pith_short_16","alias_value":"U7WRXIV77CDCMQGV","created_at":"2026-07-05T06:02:08Z"},{"alias_kind":"pith_short_8","alias_value":"U7WRXIV7","created_at":"2026-07-05T06:02:08Z"}],"graph_snapshots":[{"event_id":"sha256:b085a27dbc3de7aff034ca247c079acba8f8c55111ac13eff67e42ab0fe681d8","target":"graph","created_at":"2026-07-05T06:02:08Z","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/2303.16727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scale is the primary factor for building a powerful foundation model that could well generalize to a variety of downstream tasks. However, it is still challenging to train video foundation models with billions of parameters. This paper shows that video masked autoencoder (VideoMAE) is a scalable and general self-supervised pre-trainer for building video foundation models. We scale the VideoMAE in both model and data with a core design. Specifically, we present a dual masking strategy for efficient pre-training, with an encoder operating on a subset of video tokens and a decoder processing anot","authors_text":"Bingkun Huang, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yu Qiao, Zhan Tong, Zhiyu Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T14:28:41Z","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16727","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":"sha256:1c1a5a648800da26c4a3ddb79dd5dd460a6349e0efed4204cab78c6cfc13a64f","target":"record","created_at":"2026-07-05T06:02:08Z","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":"6bfbb91612903815b1a00a889e065180c874a87046aef7c1c432fd4b2db9f068","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T14:28:41Z","title_canon_sha256":"23f44789a816106431635bc5bd0b52a7c11b111ec61d24c672dd50f3481378c1"},"schema_version":"1.0","source":{"id":"2303.16727","kind":"arxiv","version":2}},"canonical_sha256":"a7ed1ba2bff8862640d5bf1e2bb7612968300af68932ef35459eaa49c0e09f1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7ed1ba2bff8862640d5bf1e2bb7612968300af68932ef35459eaa49c0e09f1b","first_computed_at":"2026-07-05T06:02:08.952887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:08.952887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5IGLCSyG290lQMtSe6I6V5gk7zoUvlsH96za33qvLpVwY9sQOiCl41fITdvep4aF2BA0/eLTfb7rntGqG2FBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:08.953369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c1a5a648800da26c4a3ddb79dd5dd460a6349e0efed4204cab78c6cfc13a64f","sha256:b085a27dbc3de7aff034ca247c079acba8f8c55111ac13eff67e42ab0fe681d8"],"state_sha256":"35b64d7760e7ff559642a44604600dad7ba10ea7ef68e20307179c4b392db63f"}