{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4SUUPXFFHQWRLJEYBJGNFNWLAD","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":"2dbfea5b8af6064d6a3194dac8f60dd8d5a7b36727e74c652ea5b319fbbaf17c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T17:55:10Z","title_canon_sha256":"0086e8235825feeb15c607302e68bb38086f8ab58715ed81414e1e5f9ee68c9e"},"schema_version":"1.0","source":{"id":"2203.12602","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12602","created_at":"2026-07-05T05:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12602v3","created_at":"2026-07-05T05:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12602","created_at":"2026-07-05T05:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"4SUUPXFFHQWR","created_at":"2026-07-05T05:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"4SUUPXFFHQWRLJEY","created_at":"2026-07-05T05:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"4SUUPXFF","created_at":"2026-07-05T05:07:40Z"}],"graph_snapshots":[{"event_id":"sha256:f39ea266ef5fbd9404074104a21d259956b2aefcd5d8c1ba7b3d4b0907696956","target":"graph","created_at":"2026-07-05T05:07:40Z","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/2203.12602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three i","authors_text":"Jue Wang, Limin Wang, Yibing Song, Zhan Tong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T17:55:10Z","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12602","kind":"arxiv","version":3},"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":"sha256:6e3d3d758b7ae859dd73b5223121d8493d9cf8ee3131d4daa72f6f463bfd7b9a","target":"record","created_at":"2026-07-05T05:07:40Z","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":"2dbfea5b8af6064d6a3194dac8f60dd8d5a7b36727e74c652ea5b319fbbaf17c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-23T17:55:10Z","title_canon_sha256":"0086e8235825feeb15c607302e68bb38086f8ab58715ed81414e1e5f9ee68c9e"},"schema_version":"1.0","source":{"id":"2203.12602","kind":"arxiv","version":3}},"canonical_sha256":"e4a947dca53c2d15a4980a4cd2b6cb00f8d95be9a7662aff396151bbd435a0a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4a947dca53c2d15a4980a4cd2b6cb00f8d95be9a7662aff396151bbd435a0a8","first_computed_at":"2026-07-05T05:07:40.654324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:40.654324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OyXUWy0JHwD2rEJ6p8OHolA9JDI250+qtemeXlhcXPQxmb+zKWD4dFAPFFnAHDfMXhSwACxAqprJqqdzYbleAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:40.654936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.12602","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e3d3d758b7ae859dd73b5223121d8493d9cf8ee3131d4daa72f6f463bfd7b9a","sha256:f39ea266ef5fbd9404074104a21d259956b2aefcd5d8c1ba7b3d4b0907696956"],"state_sha256":"365e6e5ad004305aa380f556147f89e2f45c8b81a57a019eb67e76c0b63cd25b"}