{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LYKBM2F6WGQA65P4DWDPSDG3LN","short_pith_number":"pith:LYKBM2F6","schema_version":"1.0","canonical_sha256":"5e141668beb1a00f75fc1d86f90cdb5b53d85124a6e56470f2b4868c047eea02","source":{"kind":"arxiv","id":"2408.06687","version":3},"attestation_state":"computed","paper":{"title":"Masked Image Modeling: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Florinel Alin Croitoru, Nicu Sebe, Radu Tudor Ionescu, Shervin Minaee, Vlad Hondru","submitted_at":"2024-08-13T07:27:02Z","abstract_excerpt":"In this work, we survey recent studies on masked image modeling (MIM), an approach that emerged as a powerful self-supervised learning technique in computer vision. The MIM task involves masking some information, e.g. pixels, patches, or even latent representations, and training a model, usually an autoencoder, to predicting the missing information by using the context available in the visible part of the input. We identify and formalize two categories of approaches on how to implement MIM as a pretext task, one based on reconstruction and one based on contrastive learning. Then, we construct "},"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":"2408.06687","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T07:27:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bba5636c72ec5642c12ad71daea5c3739a1d34b6a096f6eee5637e4b0413ca5a","abstract_canon_sha256":"b9b6a7a8ec5e82e79a8a3327eebcbbf7cc91bf568515d98c06cddbb8197a8944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:42.966193Z","signature_b64":"DGxgF+zPWaVDkYkraG5vxWKyI3Kv2cnY1kazU1nL2wuKrxO8ZEsXSwidUWp8NDhRr78/qBker61d4yAZ/IAGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e141668beb1a00f75fc1d86f90cdb5b53d85124a6e56470f2b4868c047eea02","last_reissued_at":"2026-07-05T11:34:42.965723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:42.965723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Image Modeling: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Florinel Alin Croitoru, Nicu Sebe, Radu Tudor Ionescu, Shervin Minaee, Vlad Hondru","submitted_at":"2024-08-13T07:27:02Z","abstract_excerpt":"In this work, we survey recent studies on masked image modeling (MIM), an approach that emerged as a powerful self-supervised learning technique in computer vision. The MIM task involves masking some information, e.g. pixels, patches, or even latent representations, and training a model, usually an autoencoder, to predicting the missing information by using the context available in the visible part of the input. We identify and formalize two categories of approaches on how to implement MIM as a pretext task, one based on reconstruction and one based on contrastive learning. Then, we construct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06687","kind":"arxiv","version":3},"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/2408.06687/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":"2408.06687","created_at":"2026-07-05T11:34:42.965780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06687v3","created_at":"2026-07-05T11:34:42.965780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06687","created_at":"2026-07-05T11:34:42.965780+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYKBM2F6WGQA","created_at":"2026-07-05T11:34:42.965780+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYKBM2F6WGQA65P4","created_at":"2026-07-05T11:34:42.965780+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYKBM2F6","created_at":"2026-07-05T11:34:42.965780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18270","citing_title":"Adaptive Mask-guided K-space Diffusion for Accelerated MRI Reconstruction","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN","json":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN.json","graph_json":"https://pith.science/api/pith-number/LYKBM2F6WGQA65P4DWDPSDG3LN/graph.json","events_json":"https://pith.science/api/pith-number/LYKBM2F6WGQA65P4DWDPSDG3LN/events.json","paper":"https://pith.science/paper/LYKBM2F6"},"agent_actions":{"view_html":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN","download_json":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN.json","view_paper":"https://pith.science/paper/LYKBM2F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06687&json=true","fetch_graph":"https://pith.science/api/pith-number/LYKBM2F6WGQA65P4DWDPSDG3LN/graph.json","fetch_events":"https://pith.science/api/pith-number/LYKBM2F6WGQA65P4DWDPSDG3LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN/action/storage_attestation","attest_author":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN/action/author_attestation","sign_citation":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN/action/citation_signature","submit_replication":"https://pith.science/pith/LYKBM2F6WGQA65P4DWDPSDG3LN/action/replication_record"}},"created_at":"2026-07-05T11:34:42.965780+00:00","updated_at":"2026-07-05T11:34:42.965780+00:00"}