{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUA66PR65ZOXSKVTKT4DAPR32Z","short_pith_number":"pith:CUA66PR6","schema_version":"1.0","canonical_sha256":"1501ef3e3eee5d792ab354f8303e3bd66d6fca179c7ce3920c57e2b0a350daf2","source":{"kind":"arxiv","id":"2507.19773","version":1},"attestation_state":"computed","paper":{"title":"Self-Guided Masked Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Inseo Lee, Jeongwoo Shin, Joonseok Lee, Junho Lee","submitted_at":"2025-07-26T03:48:12Z","abstract_excerpt":"Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly learns. In this paper, with an in-depth analysis, we discover that MAE intrinsically learns pattern-based patch-level clustering from surprisingly early stages of pretraining. Upon this understanding, we propose self-guided masked autoencoder, which internally generates informed mask by utilizing its progress in patch clustering, substituting the naive random m"},"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":"2507.19773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T03:48:12Z","cross_cats_sorted":[],"title_canon_sha256":"4b1b5429ac9dc9075fd7b2d484a63d4f25e9cfa4cfbbaac71ca4333714150675","abstract_canon_sha256":"47575bd0106e60b711920d0b6d6b4c845e262436e18194f7d42a30b8b22f5c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:41.687308Z","signature_b64":"ppi2oV5Lvuo9G2uBkzotEY4B9fFfsZHy7Wrmnsbd4zDAKsmWXZUJ5ItYn9w6oDfOgQPDbohVFaxP+KLPeuKXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1501ef3e3eee5d792ab354f8303e3bd66d6fca179c7ce3920c57e2b0a350daf2","last_reissued_at":"2026-07-05T11:43:41.686890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:41.686890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Guided Masked Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Inseo Lee, Jeongwoo Shin, Joonseok Lee, Junho Lee","submitted_at":"2025-07-26T03:48:12Z","abstract_excerpt":"Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly learns. In this paper, with an in-depth analysis, we discover that MAE intrinsically learns pattern-based patch-level clustering from surprisingly early stages of pretraining. Upon this understanding, we propose self-guided masked autoencoder, which internally generates informed mask by utilizing its progress in patch clustering, substituting the naive random m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19773","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/2507.19773/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":"2507.19773","created_at":"2026-07-05T11:43:41.686961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19773v1","created_at":"2026-07-05T11:43:41.686961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19773","created_at":"2026-07-05T11:43:41.686961+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUA66PR65ZOX","created_at":"2026-07-05T11:43:41.686961+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUA66PR65ZOXSKVT","created_at":"2026-07-05T11:43:41.686961+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUA66PR6","created_at":"2026-07-05T11:43:41.686961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z","json":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z.json","graph_json":"https://pith.science/api/pith-number/CUA66PR65ZOXSKVTKT4DAPR32Z/graph.json","events_json":"https://pith.science/api/pith-number/CUA66PR65ZOXSKVTKT4DAPR32Z/events.json","paper":"https://pith.science/paper/CUA66PR6"},"agent_actions":{"view_html":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z","download_json":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z.json","view_paper":"https://pith.science/paper/CUA66PR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19773&json=true","fetch_graph":"https://pith.science/api/pith-number/CUA66PR65ZOXSKVTKT4DAPR32Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CUA66PR65ZOXSKVTKT4DAPR32Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z/action/storage_attestation","attest_author":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z/action/author_attestation","sign_citation":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z/action/citation_signature","submit_replication":"https://pith.science/pith/CUA66PR65ZOXSKVTKT4DAPR32Z/action/replication_record"}},"created_at":"2026-07-05T11:43:41.686961+00:00","updated_at":"2026-07-05T11:43:41.686961+00:00"}