{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VR37FNSXUQI3NMZOZJC4NULEZO","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":"05d1fedbcdae6bcb4fef2fc47bc2701cd5530ab4eee8e41588997dc1ceae5287","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-23T17:59:33Z","title_canon_sha256":"76d3ff9d0a7791a744b1ab4fd60b86aa35dd82890961ac3670002e4fdb5f45c6"},"schema_version":"1.0","source":{"id":"2206.11894","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.11894","created_at":"2026-07-05T04:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2206.11894v2","created_at":"2026-07-05T04:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11894","created_at":"2026-07-05T04:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"VR37FNSXUQI3","created_at":"2026-07-05T04:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"VR37FNSXUQI3NMZO","created_at":"2026-07-05T04:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"VR37FNSX","created_at":"2026-07-05T04:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:92aa7c60f74c821ce78707b920e991b1a0813f7c2c59a8e2cb34e63aff3862ad","target":"graph","created_at":"2026-07-05T04:46:38Z","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/2206.11894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video prediction models by pre-training transformers via masked visual modeling. Our approach, named MaskViT, is based on two simple design decisions. First, for memory and training efficiency, we use two types of window attention: spatial and spatiotemporal. Second, during training, we mask a variable percentage of tokens instead of a fixed mask ratio. For infere","authors_text":"Agrim Gupta, Jiajun Wu, Li Fei-Fei, Roberto Mart\\'in-Mart\\'in, Stephen Tian, Yunzhi Zhang","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-23T17:59:33Z","title":"MaskViT: Masked Visual Pre-Training for Video Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11894","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":"sha256:70ec5486455796cb34bddf3e81c6f3113d211933c06e9e4de63e5b9d83d38522","target":"record","created_at":"2026-07-05T04:46:38Z","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":"05d1fedbcdae6bcb4fef2fc47bc2701cd5530ab4eee8e41588997dc1ceae5287","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-23T17:59:33Z","title_canon_sha256":"76d3ff9d0a7791a744b1ab4fd60b86aa35dd82890961ac3670002e4fdb5f45c6"},"schema_version":"1.0","source":{"id":"2206.11894","kind":"arxiv","version":2}},"canonical_sha256":"ac77f2b657a411b6b32eca45c6d164cbbbc7ff39f083ca7f301d3f6169ff3875","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac77f2b657a411b6b32eca45c6d164cbbbc7ff39f083ca7f301d3f6169ff3875","first_computed_at":"2026-07-05T04:46:38.623981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:38.623981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4nnJqqVgMvuFdwlRgaTLVcCmI26kBSQy0VMdQ4eFd5WfU2oRDW4QhvMItxtJrcX8PcMhVFXrwToMD0VW6jUeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:38.624495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.11894","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70ec5486455796cb34bddf3e81c6f3113d211933c06e9e4de63e5b9d83d38522","sha256:92aa7c60f74c821ce78707b920e991b1a0813f7c2c59a8e2cb34e63aff3862ad"],"state_sha256":"2c7a2feff28185ff0c6f3bcee0803d739c06a6bc078ac37a60f1643f8737f1d3"}