{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSUR6BUWNZ2O3HEWSCXIHLAAU5","short_pith_number":"pith:XSUR6BUW","schema_version":"1.0","canonical_sha256":"bca91f06966e74ed9c9690ae83ac00a77c913f17104d415e5236f489d214eb9f","source":{"kind":"arxiv","id":"2310.01994","version":2},"attestation_state":"computed","paper":{"title":"Understanding Masked Autoencoders From a Local Contrastive Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangmiao Pang, Lei Bai, Luping Zhou, Meng Wei, Wanli Ouyang, Xiaoyu Yue, Xihui Liu","submitted_at":"2023-10-03T12:08:15Z","abstract_excerpt":"Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across various downstream vision tasks, the underlying mechanisms that drive MAE's efficacy are less well-explored compared to the canonical contrastive learning paradigm. In this paper, we first propose a local perspective to explicitly extract a local contrastive form from MAE's reconstructive objective at the patch level. And then we introduce a new empirical framework, called Local Cont"},"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":"2310.01994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T12:08:15Z","cross_cats_sorted":[],"title_canon_sha256":"a4a7df5550bc809b40f4f8d3ffc946ad8c4750e3ad3db041211e7af39caf4ebf","abstract_canon_sha256":"039a48e3d44d8432c5dc78fc62d9089455a33efe51bb1a686f376f75e161b1b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:45.054169Z","signature_b64":"7/ssu5JrnNXZ2JNVfyDEIMvpOMlAWbMgaRS6uERT8CbyPAzbQ4atrampCQVkoaWDfppO6QOv8yX+dDfzCFoUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca91f06966e74ed9c9690ae83ac00a77c913f17104d415e5236f489d214eb9f","last_reissued_at":"2026-07-05T07:21:45.053602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:45.053602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Masked Autoencoders From a Local Contrastive Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangmiao Pang, Lei Bai, Luping Zhou, Meng Wei, Wanli Ouyang, Xiaoyu Yue, Xihui Liu","submitted_at":"2023-10-03T12:08:15Z","abstract_excerpt":"Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across various downstream vision tasks, the underlying mechanisms that drive MAE's efficacy are less well-explored compared to the canonical contrastive learning paradigm. In this paper, we first propose a local perspective to explicitly extract a local contrastive form from MAE's reconstructive objective at the patch level. And then we introduce a new empirical framework, called Local Cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01994","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/2310.01994/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":"2310.01994","created_at":"2026-07-05T07:21:45.053662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01994v2","created_at":"2026-07-05T07:21:45.053662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01994","created_at":"2026-07-05T07:21:45.053662+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSUR6BUWNZ2O","created_at":"2026-07-05T07:21:45.053662+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSUR6BUWNZ2O3HEW","created_at":"2026-07-05T07:21:45.053662+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSUR6BUW","created_at":"2026-07-05T07:21:45.053662+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/XSUR6BUWNZ2O3HEWSCXIHLAAU5","json":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5.json","graph_json":"https://pith.science/api/pith-number/XSUR6BUWNZ2O3HEWSCXIHLAAU5/graph.json","events_json":"https://pith.science/api/pith-number/XSUR6BUWNZ2O3HEWSCXIHLAAU5/events.json","paper":"https://pith.science/paper/XSUR6BUW"},"agent_actions":{"view_html":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5","download_json":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5.json","view_paper":"https://pith.science/paper/XSUR6BUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01994&json=true","fetch_graph":"https://pith.science/api/pith-number/XSUR6BUWNZ2O3HEWSCXIHLAAU5/graph.json","fetch_events":"https://pith.science/api/pith-number/XSUR6BUWNZ2O3HEWSCXIHLAAU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5/action/storage_attestation","attest_author":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5/action/author_attestation","sign_citation":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5/action/citation_signature","submit_replication":"https://pith.science/pith/XSUR6BUWNZ2O3HEWSCXIHLAAU5/action/replication_record"}},"created_at":"2026-07-05T07:21:45.053662+00:00","updated_at":"2026-07-05T07:21:45.053662+00:00"}