{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PHOTDSNL76OWJSHYBKFRRIPFEM","short_pith_number":"pith:PHOTDSNL","schema_version":"1.0","canonical_sha256":"79dd31c9abff9d64c8f80a8b18a1e52322a5b0500e69394ff6b27e35a416c99f","source":{"kind":"arxiv","id":"2205.10063","version":1},"attestation_state":"computed","paper":{"title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Lingfeng Yang, Wenhai Wang, Xiang Li","submitted_at":"2022-05-20T10:16:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.10063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-20T10:16:30Z","cross_cats_sorted":[],"title_canon_sha256":"d9bda66d587e7dfae0eed412526b96666e692f1c47d60f2a3eefb7524837f941","abstract_canon_sha256":"ee652d8f7e46f230c2e45543202457689d517218b79479735cdb89fa66d81fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:02.959535Z","signature_b64":"/qSxU3nlBr5uKE/18EaiFBcX40LpeHwpYkXKGCLIF0jHdSxZT/p+CrkSYLvNouKEoPJxai8aEitGKOVguX/PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79dd31c9abff9d64c8f80a8b18a1e52322a5b0500e69394ff6b27e35a416c99f","last_reissued_at":"2026-07-05T04:25:02.958922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:02.958922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Lingfeng Yang, Wenhai Wang, Xiang Li","submitted_at":"2022-05-20T10:16:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10063","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/2205.10063/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.10063","created_at":"2026-07-05T04:25:02.958985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10063v1","created_at":"2026-07-05T04:25:02.958985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10063","created_at":"2026-07-05T04:25:02.958985+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHOTDSNL76OW","created_at":"2026-07-05T04:25:02.958985+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHOTDSNL76OWJSHY","created_at":"2026-07-05T04:25:02.958985+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHOTDSNL","created_at":"2026-07-05T04:25:02.958985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13454","citing_title":"Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM","json":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM.json","graph_json":"https://pith.science/api/pith-number/PHOTDSNL76OWJSHYBKFRRIPFEM/graph.json","events_json":"https://pith.science/api/pith-number/PHOTDSNL76OWJSHYBKFRRIPFEM/events.json","paper":"https://pith.science/paper/PHOTDSNL"},"agent_actions":{"view_html":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM","download_json":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM.json","view_paper":"https://pith.science/paper/PHOTDSNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10063&json=true","fetch_graph":"https://pith.science/api/pith-number/PHOTDSNL76OWJSHYBKFRRIPFEM/graph.json","fetch_events":"https://pith.science/api/pith-number/PHOTDSNL76OWJSHYBKFRRIPFEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM/action/storage_attestation","attest_author":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM/action/author_attestation","sign_citation":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM/action/citation_signature","submit_replication":"https://pith.science/pith/PHOTDSNL76OWJSHYBKFRRIPFEM/action/replication_record"}},"created_at":"2026-07-05T04:25:02.958985+00:00","updated_at":"2026-07-05T04:25:02.958985+00:00"}