{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PHOTDSNL76OWJSHYBKFRRIPFEM","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":"ee652d8f7e46f230c2e45543202457689d517218b79479735cdb89fa66d81fc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-20T10:16:30Z","title_canon_sha256":"d9bda66d587e7dfae0eed412526b96666e692f1c47d60f2a3eefb7524837f941"},"schema_version":"1.0","source":{"id":"2205.10063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10063","created_at":"2026-07-05T04:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10063v1","created_at":"2026-07-05T04:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10063","created_at":"2026-07-05T04:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"PHOTDSNL76OW","created_at":"2026-07-05T04:25:02Z"},{"alias_kind":"pith_short_16","alias_value":"PHOTDSNL76OWJSHY","created_at":"2026-07-05T04:25:02Z"},{"alias_kind":"pith_short_8","alias_value":"PHOTDSNL","created_at":"2026-07-05T04:25:02Z"}],"graph_snapshots":[{"event_id":"sha256:ac3fc8a67dd3e9042d0e65092291f4813120c467bff47cec97c8e8e4ce8417be","target":"graph","created_at":"2026-07-05T04:25:02Z","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/2205.10063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-training efficiency and fine-tuning accuracy. Notably, the success of the asymmetric structure relies on the \"global\" property of Vanilla Vision Transformer (ViT), whose self-attention mechanism reasons over arbitrary subset of discrete image patches. However, it is still unclear how the advanced Pyramid-based ViTs (e.g., PVT, Swin) can be adopted in MAE pre-training as they commonly introduce operators within \"local\" w","authors_text":"Jian Yang, Lingfeng Yang, Wenhai Wang, Xiang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-20T10:16:30Z","title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10063","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:d9f2c6a87a0fc7408a66919f6de639b066f048d1f3c4df0958435dede5468f2f","target":"record","created_at":"2026-07-05T04:25:02Z","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":"ee652d8f7e46f230c2e45543202457689d517218b79479735cdb89fa66d81fc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-20T10:16:30Z","title_canon_sha256":"d9bda66d587e7dfae0eed412526b96666e692f1c47d60f2a3eefb7524837f941"},"schema_version":"1.0","source":{"id":"2205.10063","kind":"arxiv","version":1}},"canonical_sha256":"79dd31c9abff9d64c8f80a8b18a1e52322a5b0500e69394ff6b27e35a416c99f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79dd31c9abff9d64c8f80a8b18a1e52322a5b0500e69394ff6b27e35a416c99f","first_computed_at":"2026-07-05T04:25:02.958922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:02.958922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/qSxU3nlBr5uKE/18EaiFBcX40LpeHwpYkXKGCLIF0jHdSxZT/p+CrkSYLvNouKEoPJxai8aEitGKOVguX/PDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:02.959535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9f2c6a87a0fc7408a66919f6de639b066f048d1f3c4df0958435dede5468f2f","sha256:ac3fc8a67dd3e9042d0e65092291f4813120c467bff47cec97c8e8e4ce8417be"],"state_sha256":"ee062c6c362f78896a0fc48440e7e3406ea2a92f6e15cf827e628887211b36ff"}