{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ITUKR4YJ5ER5YR756IDGX4RHXT","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":"b4a91cba97d5600ab7512570aad7b55655cc19c4d1a39998863ca066d731284f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T04:00:42Z","title_canon_sha256":"956faf1e2318b13e6daa1dcfcfeccb0f76429e4fbba81b03f173dcda754b6ce6"},"schema_version":"1.0","source":{"id":"2205.13137","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13137","created_at":"2026-07-05T05:56:38Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13137v4","created_at":"2026-07-05T05:56:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13137","created_at":"2026-07-05T05:56:38Z"},{"alias_kind":"pith_short_12","alias_value":"ITUKR4YJ5ER5","created_at":"2026-07-05T05:56:38Z"},{"alias_kind":"pith_short_16","alias_value":"ITUKR4YJ5ER5YR75","created_at":"2026-07-05T05:56:38Z"},{"alias_kind":"pith_short_8","alias_value":"ITUKR4YJ","created_at":"2026-07-05T05:56:38Z"}],"graph_snapshots":[{"event_id":"sha256:17e15fc8506b44ab2499f80a243e99b15ff5fab3ea133ee695d15776ed135150","target":"graph","created_at":"2026-07-05T05:56:38Z","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/2205.13137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers. Existing masked image modeling (MIM) methods for hierarchical Vision Transformers replace a random subset of input tokens with a special [MASK] symbol and aim at reconstructing original image tokens from the corrupted image. However, we find that using the [MASK] symbol greatly slows down the training and causes pretraining-finetuning inconsistency, due to the large masking ratio (e.g., 60% in SimMIM). On the other hand, MAE ","authors_text":"Hongsheng Li, Jihao Liu, Jinliang Zheng, Xin Huang, Yu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T04:00:42Z","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13137","kind":"arxiv","version":4},"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:c7624cc15c430227a1fb13af51b52d00ddcc77e6f341f372e668a9b8813cbb47","target":"record","created_at":"2026-07-05T05:56:38Z","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":"b4a91cba97d5600ab7512570aad7b55655cc19c4d1a39998863ca066d731284f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T04:00:42Z","title_canon_sha256":"956faf1e2318b13e6daa1dcfcfeccb0f76429e4fbba81b03f173dcda754b6ce6"},"schema_version":"1.0","source":{"id":"2205.13137","kind":"arxiv","version":4}},"canonical_sha256":"44e8a8f309e923dc47fdf2066bf227bce23c428f15d4590a92063f4acc83da93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44e8a8f309e923dc47fdf2066bf227bce23c428f15d4590a92063f4acc83da93","first_computed_at":"2026-07-05T05:56:38.350914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:38.350914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+BGcDfFkMEN1fiTTKwnT3/08vyKI3B+LXDLb9jzCvJM1OnYoAA50k2/cPVq6TVAlxItakHtgKZ5+MoyyuxiEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:38.351357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13137","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7624cc15c430227a1fb13af51b52d00ddcc77e6f341f372e668a9b8813cbb47","sha256:17e15fc8506b44ab2499f80a243e99b15ff5fab3ea133ee695d15776ed135150"],"state_sha256":"b7ef5595de4e18565e5c481d5f3dc1c00a28dc23be79515826b77987df5521d4"}