{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LGO32AIIXMJGAT3OGFBB5DIC2J","short_pith_number":"pith:LGO32AII","schema_version":"1.0","canonical_sha256":"599dbd0108bb12604f6e31421e8d02d2584ccb4c3f51871e421094cc26994345","source":{"kind":"arxiv","id":"2303.02416","version":2},"attestation_state":"computed","paper":{"title":"PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiacheng Chen, Kai Chen, Songyang Zhang, Yuan Liu","submitted_at":"2023-03-04T13:38:51Z","abstract_excerpt":"Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, {\\ourmethod}, that e"},"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":"2303.02416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T13:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"bf5dd4b516381c5000b5af0a3ebadc0823c4b49f9b003a1fce99abc4645db294","abstract_canon_sha256":"c50a538ec261126f2d7b43ee10df994dc91bd7b0246f3e67c3f03495bc89d165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:15.632894Z","signature_b64":"fi816cWwO8oqlB4MNFSY9fQ73CWVsxsPJGaTr57i5+ggb0poyeUy9vJWb1kAbQ4LzS9hK0/dY2MqBtGKK70xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599dbd0108bb12604f6e31421e8d02d2584ccb4c3f51871e421094cc26994345","last_reissued_at":"2026-07-05T05:54:15.632355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:15.632355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiacheng Chen, Kai Chen, Songyang Zhang, Yuan Liu","submitted_at":"2023-03-04T13:38:51Z","abstract_excerpt":"Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, {\\ourmethod}, that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02416","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/2303.02416/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":"2303.02416","created_at":"2026-07-05T05:54:15.632429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02416v2","created_at":"2026-07-05T05:54:15.632429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02416","created_at":"2026-07-05T05:54:15.632429+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGO32AIIXMJG","created_at":"2026-07-05T05:54:15.632429+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGO32AIIXMJGAT3O","created_at":"2026-07-05T05:54:15.632429+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGO32AII","created_at":"2026-07-05T05:54:15.632429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16086","citing_title":"Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J","json":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J.json","graph_json":"https://pith.science/api/pith-number/LGO32AIIXMJGAT3OGFBB5DIC2J/graph.json","events_json":"https://pith.science/api/pith-number/LGO32AIIXMJGAT3OGFBB5DIC2J/events.json","paper":"https://pith.science/paper/LGO32AII"},"agent_actions":{"view_html":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J","download_json":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J.json","view_paper":"https://pith.science/paper/LGO32AII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02416&json=true","fetch_graph":"https://pith.science/api/pith-number/LGO32AIIXMJGAT3OGFBB5DIC2J/graph.json","fetch_events":"https://pith.science/api/pith-number/LGO32AIIXMJGAT3OGFBB5DIC2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J/action/storage_attestation","attest_author":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J/action/author_attestation","sign_citation":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J/action/citation_signature","submit_replication":"https://pith.science/pith/LGO32AIIXMJGAT3OGFBB5DIC2J/action/replication_record"}},"created_at":"2026-07-05T05:54:15.632429+00:00","updated_at":"2026-07-05T05:54:15.632429+00:00"}