{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZMV4QR3JF77AAFUGUOQHRIWULU","short_pith_number":"pith:ZMV4QR3J","canonical_record":{"source":{"id":"2401.15900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"fa5ee45ceb08f1b6fc288b8f22a972d159c352a1b7c59d4a336f37990760b15c","abstract_canon_sha256":"6dccbdf6643956625f2fc2234dec1a2feb4cd599c1ea35d73a5acc19f1adea19"},"schema_version":"1.0"},"canonical_sha256":"cb2bc847692ffe001686a3a078a2d45d13bc4aaedd546b3ab15ac8623f4a7445","source":{"kind":"arxiv","id":"2401.15900","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZMV4QR3JF77AAFUGUOQHRIWULU","target":"record","payload":{"canonical_record":{"source":{"id":"2401.15900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"fa5ee45ceb08f1b6fc288b8f22a972d159c352a1b7c59d4a336f37990760b15c","abstract_canon_sha256":"6dccbdf6643956625f2fc2234dec1a2feb4cd599c1ea35d73a5acc19f1adea19"},"schema_version":"1.0"},"canonical_sha256":"cb2bc847692ffe001686a3a078a2d45d13bc4aaedd546b3ab15ac8623f4a7445","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:41.160783Z","signature_b64":"SGVttQdBsDY9XZjMFGVfGG6yKwuA/gY9+xudWHKPQKxzqWGMjZqlZz/hDOXHpEwAYiSqt0Iigt+7TyrXEUQNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb2bc847692ffe001686a3a078a2d45d13bc4aaedd546b3ab15ac8623f4a7445","last_reissued_at":"2026-07-05T07:38:41.160368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:41.160368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.15900","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//U+7djyc1Zx8w+ZFDpWv6N2Tdg33+OK5Z3fQcWVSQt9oQEw3FbMSZriRu610cS/tZ+hxBCffVmHaMwmhjoGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:53.167373Z"},"content_sha256":"3cbec46e007f8c5231b0af56bca37ae5651af721d0b2609d99bf2140f4e3181e","schema_version":"1.0","event_id":"sha256:3cbec46e007f8c5231b0af56bca37ae5651af721d0b2609d99bf2140f4e3181e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZMV4QR3JF77AAFUGUOQHRIWULU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MV2MAE: Multi-View Video Masked Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Xu, Ketul Shah, Marian George, Mayank Bansal, Peng Zhou, Rama Chellappa, Robert Crandall","submitted_at":"2024-01-29T05:58:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15900","kind":"arxiv","version":1},"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/2401.15900/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StDtj+AeTR8Ja0qxnJmQnIgOi3PVww9bmbCCYM+Tt0FIqN9SRuU+xA1w582S4D+5fWRJeXBS32bavjCXKQEWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:53.167949Z"},"content_sha256":"ce8d34f6337071700feab89b4facd7c1eb9b469865d549bdc83a4e6b0da86e68","schema_version":"1.0","event_id":"sha256:ce8d34f6337071700feab89b4facd7c1eb9b469865d549bdc83a4e6b0da86e68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/bundle.json","state_url":"https://pith.science/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:50:53Z","links":{"resolver":"https://pith.science/pith/ZMV4QR3JF77AAFUGUOQHRIWULU","bundle":"https://pith.science/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/bundle.json","state":"https://pith.science/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMV4QR3JF77AAFUGUOQHRIWULU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnWFTC9yHESsvWs11bWEBwlw+Ru2W1WuhEXMADDBblMWnK+1DeLjrXaN5PoK3WvErn7qlO3lK5AErCDlhjSuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:50:53.171846Z","bundle_sha256":"0938a612336dabdf7868847553e7af9cfe45f718d3f436b629392d4c629c91b4"}}