{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UY5EMRF45ZZMCPBCUQSAJKTOOQ","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":"d9ada401340f568b5ae8b0146aa4537c34077b423e6b1d7e4ddadcbdbf9cea64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-25T18:49:57Z","title_canon_sha256":"93e34e1fc5657002e895aa1609ec398b84ecf117ded0b5271bd46686149d8433"},"schema_version":"1.0","source":{"id":"2401.14391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14391","created_at":"2026-07-05T10:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14391v2","created_at":"2026-07-05T10:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14391","created_at":"2026-07-05T10:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"UY5EMRF45ZZM","created_at":"2026-07-05T10:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"UY5EMRF45ZZMCPBC","created_at":"2026-07-05T10:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"UY5EMRF4","created_at":"2026-07-05T10:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:78d266f0417e368436001e2a0a8659d66365d29ac9f917be87fe48ae3e25e666","target":"graph","created_at":"2026-07-05T10:46:53Z","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/2401.14391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we examine the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning. We decompose the decoding mechanism for masked reconstruction into self-attention between mask tokens and cross-attention between masked and visible tokens. Our findings reveal that MAE reconstructs coherent images from visible patches not through interactions between patches in the decoder but by learning a global representation within the encoder. This discovery leads us to propose a simple visual pretraining framework: cross-attention masked autoencoders (C","authors_text":"Adam Yala, Alexei A. Efros, Baifeng Shi, Ken Goldberg, Letian Fu, Long Lian, Renhao Wang, Trevor Darrell, Xudong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-25T18:49:57Z","title":"Rethinking Patch Dependence for Masked Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14391","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":"sha256:961136c454777325d7d6b22693ea38a86b00a7d584f9c51ec5da9f978711f6e7","target":"record","created_at":"2026-07-05T10:46:53Z","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":"d9ada401340f568b5ae8b0146aa4537c34077b423e6b1d7e4ddadcbdbf9cea64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-25T18:49:57Z","title_canon_sha256":"93e34e1fc5657002e895aa1609ec398b84ecf117ded0b5271bd46686149d8433"},"schema_version":"1.0","source":{"id":"2401.14391","kind":"arxiv","version":2}},"canonical_sha256":"a63a4644bcee72c13c22a42404aa6e740aa390bf7e9c0b78d920e7f0ed556ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a63a4644bcee72c13c22a42404aa6e740aa390bf7e9c0b78d920e7f0ed556ecf","first_computed_at":"2026-07-05T10:46:53.402597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:53.402597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5vooQE6kBOcMytE9NfmeWoPVOioa1Z4SK9wtCzg3ysPSWqDKQPSNjEJmNFEpLlbqCVOizbUzuHA0EVQ1/RF5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:53.403199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:961136c454777325d7d6b22693ea38a86b00a7d584f9c51ec5da9f978711f6e7","sha256:78d266f0417e368436001e2a0a8659d66365d29ac9f917be87fe48ae3e25e666"],"state_sha256":"568bdd0a8a13ea429d150974d9e8fd8550a545277f9b1f99cbbf782a8c14c336"}