{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZMV4QR3JF77AAFUGUOQHRIWULU","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":"6dccbdf6643956625f2fc2234dec1a2feb4cd599c1ea35d73a5acc19f1adea19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:58:23Z","title_canon_sha256":"fa5ee45ceb08f1b6fc288b8f22a972d159c352a1b7c59d4a336f37990760b15c"},"schema_version":"1.0","source":{"id":"2401.15900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15900","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15900v1","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15900","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZMV4QR3JF77A","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZMV4QR3JF77AAFUG","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZMV4QR3J","created_at":"2026-07-05T07:38:41Z"}],"graph_snapshots":[{"event_id":"sha256:ce8d34f6337071700feab89b4facd7c1eb9b469865d549bdc83a4e6b0da86e68","target":"graph","created_at":"2026-07-05T07:38:41Z","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/2401.15900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from synchronized multi-view videos. We use a cross-view reconstruction task to inject geometry information in the model. Our approach is based on the masked autoencoder (MAE) framework. In addition to the same-view decoder, we introduce a separate cross-view decoder which leverages cross-attention mechanism to reconstruct a target viewpoint video using a video f","authors_text":"Jie Xu, Ketul Shah, Marian George, Mayank Bansal, Peng Zhou, Rama Chellappa, Robert Crandall","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:58:23Z","title":"MV2MAE: Multi-View Video Masked Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15900","kind":"arxiv","version":1},"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":"sha256:3cbec46e007f8c5231b0af56bca37ae5651af721d0b2609d99bf2140f4e3181e","target":"record","created_at":"2026-07-05T07:38:41Z","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":"6dccbdf6643956625f2fc2234dec1a2feb4cd599c1ea35d73a5acc19f1adea19","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:58:23Z","title_canon_sha256":"fa5ee45ceb08f1b6fc288b8f22a972d159c352a1b7c59d4a336f37990760b15c"},"schema_version":"1.0","source":{"id":"2401.15900","kind":"arxiv","version":1}},"canonical_sha256":"cb2bc847692ffe001686a3a078a2d45d13bc4aaedd546b3ab15ac8623f4a7445","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb2bc847692ffe001686a3a078a2d45d13bc4aaedd546b3ab15ac8623f4a7445","first_computed_at":"2026-07-05T07:38:41.160368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:41.160368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGVttQdBsDY9XZjMFGVfGG6yKwuA/gY9+xudWHKPQKxzqWGMjZqlZz/hDOXHpEwAYiSqt0Iigt+7TyrXEUQNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:41.160783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cbec46e007f8c5231b0af56bca37ae5651af721d0b2609d99bf2140f4e3181e","sha256:ce8d34f6337071700feab89b4facd7c1eb9b469865d549bdc83a4e6b0da86e68"],"state_sha256":"67fde255bb1bc7edc16c04c4fec6a09badbc36f9fc4bc6e4a6722bc8e55baaff"}