{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K44GRPE22GF627NAHJRVB7T2ZR","short_pith_number":"pith:K44GRPE2","schema_version":"1.0","canonical_sha256":"573868bc9ad18bed7da03a6350fe7acc4cc82b2c5346fe08d8acf509dca7abf6","source":{"kind":"arxiv","id":"2208.00173","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, In So Kweon, John Seon Keun Yi, Junha Song, Kang Zhang","submitted_at":"2022-07-30T09:59:28Z","abstract_excerpt":"Masked autoencoders are scalable vision learners, as the title of MAE \\cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the pa"},"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":"2208.00173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-30T09:59:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70a4bbd89644649d22a5573e5fc949001206f5ea06211d102b20b1882d357339","abstract_canon_sha256":"631e9ddaba73a96dd535f407e134c406f468b9dece4100f5c0d177049c79f95c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:48.513852Z","signature_b64":"vS7jOBOCmHpC00cvWw6fGb9/KiHm+1WJ8GZw1d8UKZDlC0a4MQL2w8K+fbIli5WwCApzHcDnXTieJ/hpHulvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573868bc9ad18bed7da03a6350fe7acc4cc82b2c5346fe08d8acf509dca7abf6","last_reissued_at":"2026-07-05T04:44:48.513359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:48.513359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, In So Kweon, John Seon Keun Yi, Junha Song, Kang Zhang","submitted_at":"2022-07-30T09:59:28Z","abstract_excerpt":"Masked autoencoders are scalable vision learners, as the title of MAE \\cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00173","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/2208.00173/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":"2208.00173","created_at":"2026-07-05T04:44:48.513416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00173v1","created_at":"2026-07-05T04:44:48.513416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00173","created_at":"2026-07-05T04:44:48.513416+00:00"},{"alias_kind":"pith_short_12","alias_value":"K44GRPE22GF6","created_at":"2026-07-05T04:44:48.513416+00:00"},{"alias_kind":"pith_short_16","alias_value":"K44GRPE22GF627NA","created_at":"2026-07-05T04:44:48.513416+00:00"},{"alias_kind":"pith_short_8","alias_value":"K44GRPE2","created_at":"2026-07-05T04:44:48.513416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18298","citing_title":"DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR","json":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR.json","graph_json":"https://pith.science/api/pith-number/K44GRPE22GF627NAHJRVB7T2ZR/graph.json","events_json":"https://pith.science/api/pith-number/K44GRPE22GF627NAHJRVB7T2ZR/events.json","paper":"https://pith.science/paper/K44GRPE2"},"agent_actions":{"view_html":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR","download_json":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR.json","view_paper":"https://pith.science/paper/K44GRPE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00173&json=true","fetch_graph":"https://pith.science/api/pith-number/K44GRPE22GF627NAHJRVB7T2ZR/graph.json","fetch_events":"https://pith.science/api/pith-number/K44GRPE22GF627NAHJRVB7T2ZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR/action/storage_attestation","attest_author":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR/action/author_attestation","sign_citation":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR/action/citation_signature","submit_replication":"https://pith.science/pith/K44GRPE22GF627NAHJRVB7T2ZR/action/replication_record"}},"created_at":"2026-07-05T04:44:48.513416+00:00","updated_at":"2026-07-05T04:44:48.513416+00:00"}