{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TUX6QHUULEY24OJU3FQT22WING","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":"bd9fb15b795a1d3cd32e116f8f0c08c2679be97bd0df9c744c31de7e0373d928","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T06:15:39Z","title_canon_sha256":"ea0bfd0961e1545522f4f0e7c7f03a5af2c67116c32cb2839fbe07184b13b7dd"},"schema_version":"1.0","source":{"id":"2502.07811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07811","created_at":"2026-07-05T10:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07811v1","created_at":"2026-07-05T10:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07811","created_at":"2026-07-05T10:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"TUX6QHUULEY2","created_at":"2026-07-05T10:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"TUX6QHUULEY24OJU","created_at":"2026-07-05T10:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"TUX6QHUU","created_at":"2026-07-05T10:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:9cea30040be47c0b648c28b95a8c0f38674ebc1b6aeac47cb0d9f346f8a0c0dc","target":"graph","created_at":"2026-07-05T10:13:10Z","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/2502.07811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook nuanced semantic attributes like specific interactions or sequences that define actions - such as action-specific features that align more closely with human cognition for space-time correspondence. This can limit the model's ability to capture the essence of certain actions that are contextually rich and continuous. Humans are capable of mapping visual concepts,","authors_text":"Daniel Harari, Liel David, Malitha Gunawardhana, Michael Sidorov, Muhammad Haris Khan, Shihab Aaqil Ahamed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T06:15:39Z","title":"CrossVideoMAE: Self-Supervised Image-Video Representation Learning with Masked Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07811","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:e727c05a45a3c363af708c15abba3d9f12484e9b4a3f2e4e97a124e9b0fe829b","target":"record","created_at":"2026-07-05T10:13:10Z","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":"bd9fb15b795a1d3cd32e116f8f0c08c2679be97bd0df9c744c31de7e0373d928","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T06:15:39Z","title_canon_sha256":"ea0bfd0961e1545522f4f0e7c7f03a5af2c67116c32cb2839fbe07184b13b7dd"},"schema_version":"1.0","source":{"id":"2502.07811","kind":"arxiv","version":1}},"canonical_sha256":"9d2fe81e945931ae3934d9613d6ac869a34523b939f8c10d4aa5e71901197cb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d2fe81e945931ae3934d9613d6ac869a34523b939f8c10d4aa5e71901197cb6","first_computed_at":"2026-07-05T10:13:10.351369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:10.351369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7YMo3LCgGkh/So7KoJqbyk2iA1WtZnNvKM/CpCWmaUtcCDWbFYe0W+sFKc4kXQC83jZzTSPC7vfDiSOlsuDhBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:10.351897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e727c05a45a3c363af708c15abba3d9f12484e9b4a3f2e4e97a124e9b0fe829b","sha256:9cea30040be47c0b648c28b95a8c0f38674ebc1b6aeac47cb0d9f346f8a0c0dc"],"state_sha256":"de39dc00b23f6c1151210a82889e6602c69fbad3c3a2203382f375ab257ae787"}