{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G5HQKL7I4LVOM2LMSFXF26EIX3","short_pith_number":"pith:G5HQKL7I","canonical_record":{"source":{"id":"2202.03670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T06:15:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5308dcc1670558f34057331e6fee1c779d015a40ae1d196bfe6cfa6548d68b88","abstract_canon_sha256":"bfe211a93e33bd290cbe44c6872998517bf00890698f306117cce6b63b0e2e3b"},"schema_version":"1.0"},"canonical_sha256":"374f052fe8e2eae6696c916e5d7888beef4b65f6bb6c5d6727951a3a955b4426","source":{"kind":"arxiv","id":"2202.03670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03670","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03670v2","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03670","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"G5HQKL7I4LVO","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"G5HQKL7I4LVOM2LM","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"G5HQKL7I","created_at":"2026-07-05T03:55:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G5HQKL7I4LVOM2LMSFXF26EIX3","target":"record","payload":{"canonical_record":{"source":{"id":"2202.03670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T06:15:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5308dcc1670558f34057331e6fee1c779d015a40ae1d196bfe6cfa6548d68b88","abstract_canon_sha256":"bfe211a93e33bd290cbe44c6872998517bf00890698f306117cce6b63b0e2e3b"},"schema_version":"1.0"},"canonical_sha256":"374f052fe8e2eae6696c916e5d7888beef4b65f6bb6c5d6727951a3a955b4426","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:32.926771Z","signature_b64":"9Pyquu1LqC+xWqxebn9k2de++847D4Xohxw3gHpW9NylXVmviUEAaAxO0Hb2qLAAu/DStjg30XaTrOUz9ttEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"374f052fe8e2eae6696c916e5d7888beef4b65f6bb6c5d6727951a3a955b4426","last_reissued_at":"2026-07-05T03:55:32.926252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:32.926252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.03670","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NL3KNLM29wG4D98Wr4bdsvoKZMzElFpIsM46HhryKR0cofO+nLAACD03RhsSK5dBHJKv/Pk+jxshyQ2f2IULBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:01:09.360110Z"},"content_sha256":"26d61e668890a21f823e27547f49732487eb9932ef6245306d9f469d3be90a7e","schema_version":"1.0","event_id":"sha256:26d61e668890a21f823e27547f49732487eb9932ef6245306d9f469d3be90a7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G5HQKL7I4LVOM2LMSFXF26EIX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Understand Masked Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David A. Clifton, Peng Xu, Shuhao Cao","submitted_at":"2022-02-08T06:15:07Z","abstract_excerpt":"\"Masked Autoencoders (MAE) Are Scalable Vision Learners\" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between visual and linguistic masked autoencoding (BERT-style) pre-trainings. However, to our knowledge, to date there are no theoretical perspectives to explain the powerful expressivity of MAE. In this paper, we, for the first time, propose a unified theoretical framework that provides a mathematical understanding for MAE. Specifically, we explain the patch-based atten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03670","kind":"arxiv","version":2},"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/2202.03670/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":"2026-07-05T03:55:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Igc5OTIUwrfAismcPrV8qR5IXZEOkThq6sfps2dxy4r972Rtibw04niXmwqZ1qfKaiGlFZm1t0yn2A5escU+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:01:09.360616Z"},"content_sha256":"6055ec007807e22a378ebb8f9a0b839152fd3d72ba6b46b446b64bf25b5dc56e","schema_version":"1.0","event_id":"sha256:6055ec007807e22a378ebb8f9a0b839152fd3d72ba6b46b446b64bf25b5dc56e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/bundle.json","state_url":"https://pith.science/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/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":"2026-08-21T07:01:09Z","links":{"resolver":"https://pith.science/pith/G5HQKL7I4LVOM2LMSFXF26EIX3","bundle":"https://pith.science/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/bundle.json","state":"https://pith.science/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5HQKL7I4LVOM2LMSFXF26EIX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G5HQKL7I4LVOM2LMSFXF26EIX3","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":"bfe211a93e33bd290cbe44c6872998517bf00890698f306117cce6b63b0e2e3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T06:15:07Z","title_canon_sha256":"5308dcc1670558f34057331e6fee1c779d015a40ae1d196bfe6cfa6548d68b88"},"schema_version":"1.0","source":{"id":"2202.03670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03670","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03670v2","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03670","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_12","alias_value":"G5HQKL7I4LVO","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_16","alias_value":"G5HQKL7I4LVOM2LM","created_at":"2026-07-05T03:55:32Z"},{"alias_kind":"pith_short_8","alias_value":"G5HQKL7I","created_at":"2026-07-05T03:55:32Z"}],"graph_snapshots":[{"event_id":"sha256:6055ec007807e22a378ebb8f9a0b839152fd3d72ba6b46b446b64bf25b5dc56e","target":"graph","created_at":"2026-07-05T03:55:32Z","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/2202.03670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"\"Masked Autoencoders (MAE) Are Scalable Vision Learners\" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between visual and linguistic masked autoencoding (BERT-style) pre-trainings. However, to our knowledge, to date there are no theoretical perspectives to explain the powerful expressivity of MAE. In this paper, we, for the first time, propose a unified theoretical framework that provides a mathematical understanding for MAE. Specifically, we explain the patch-based atten","authors_text":"David A. Clifton, Peng Xu, Shuhao Cao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T06:15:07Z","title":"How to Understand Masked Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03670","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":"sha256:26d61e668890a21f823e27547f49732487eb9932ef6245306d9f469d3be90a7e","target":"record","created_at":"2026-07-05T03:55:32Z","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":"bfe211a93e33bd290cbe44c6872998517bf00890698f306117cce6b63b0e2e3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T06:15:07Z","title_canon_sha256":"5308dcc1670558f34057331e6fee1c779d015a40ae1d196bfe6cfa6548d68b88"},"schema_version":"1.0","source":{"id":"2202.03670","kind":"arxiv","version":2}},"canonical_sha256":"374f052fe8e2eae6696c916e5d7888beef4b65f6bb6c5d6727951a3a955b4426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"374f052fe8e2eae6696c916e5d7888beef4b65f6bb6c5d6727951a3a955b4426","first_computed_at":"2026-07-05T03:55:32.926252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:32.926252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Pyquu1LqC+xWqxebn9k2de++847D4Xohxw3gHpW9NylXVmviUEAaAxO0Hb2qLAAu/DStjg30XaTrOUz9ttEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:32.926771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26d61e668890a21f823e27547f49732487eb9932ef6245306d9f469d3be90a7e","sha256:6055ec007807e22a378ebb8f9a0b839152fd3d72ba6b46b446b64bf25b5dc56e"],"state_sha256":"b6f55314f0467a31b6e2e5ad86902a7642c39580ef41be40c313f8e0f528f801"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FoXMhyokG4t/eUqd3ejKGRHVo7DOqO7AcugtqeRFd7SwiauquIPXesZMb0YAE0EOBWpLep0xNd9+LPt0VpJ8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T07:01:09.364379Z","bundle_sha256":"f6ce9165d1dbcf3ee6e70399bf02d5e013337b8d167efb66c75146bc6bb4c123"}}