{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I66YL2I4V6CBWELBONSITDV5W7","short_pith_number":"pith:I66YL2I4","schema_version":"1.0","canonical_sha256":"47bd85e91caf841b11617364898ebdb7c8c348de734ed8f0a1a8d000b0ecb94f","source":{"kind":"arxiv","id":"2304.05919","version":1},"attestation_state":"computed","paper":{"title":"Hard Patches Mining for Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jin Xie, Junsong Fan, Kaiyou Song, Yuxi Wang, Zhaoxiang Zhang","submitted_at":"2023-04-12T15:38:23Z","abstract_excerpt":"Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging pro"},"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":"2304.05919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T15:38:23Z","cross_cats_sorted":[],"title_canon_sha256":"0a1571b7322234278cd5b0b732da2e9c5b7de73c3ac4f98563ef35740aa88da2","abstract_canon_sha256":"f358372c11b434d4f58c342d98e4305e3531a1662c11aff0b5191e0a422013e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:25.699460Z","signature_b64":"WVmlMpHUucJyMa1gBdnV9dhp0weSv4HWA3GuISNu4i2yPWFdFOsf98xl7dQZYEO2F/Wsj+Tldsdb2djZQzRRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47bd85e91caf841b11617364898ebdb7c8c348de734ed8f0a1a8d000b0ecb94f","last_reissued_at":"2026-07-05T06:00:25.698918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:25.698918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hard Patches Mining for Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jin Xie, Junsong Fan, Kaiyou Song, Yuxi Wang, Zhaoxiang Zhang","submitted_at":"2023-04-12T15:38:23Z","abstract_excerpt":"Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05919","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/2304.05919/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":"2304.05919","created_at":"2026-07-05T06:00:25.698990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05919v1","created_at":"2026-07-05T06:00:25.698990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05919","created_at":"2026-07-05T06:00:25.698990+00:00"},{"alias_kind":"pith_short_12","alias_value":"I66YL2I4V6CB","created_at":"2026-07-05T06:00:25.698990+00:00"},{"alias_kind":"pith_short_16","alias_value":"I66YL2I4V6CBWELB","created_at":"2026-07-05T06:00:25.698990+00:00"},{"alias_kind":"pith_short_8","alias_value":"I66YL2I4","created_at":"2026-07-05T06:00:25.698990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06314","citing_title":"From Pixels to Components: Eigenvector Masking for Visual Representation Learning","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7","json":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7.json","graph_json":"https://pith.science/api/pith-number/I66YL2I4V6CBWELBONSITDV5W7/graph.json","events_json":"https://pith.science/api/pith-number/I66YL2I4V6CBWELBONSITDV5W7/events.json","paper":"https://pith.science/paper/I66YL2I4"},"agent_actions":{"view_html":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7","download_json":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7.json","view_paper":"https://pith.science/paper/I66YL2I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05919&json=true","fetch_graph":"https://pith.science/api/pith-number/I66YL2I4V6CBWELBONSITDV5W7/graph.json","fetch_events":"https://pith.science/api/pith-number/I66YL2I4V6CBWELBONSITDV5W7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7/action/storage_attestation","attest_author":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7/action/author_attestation","sign_citation":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7/action/citation_signature","submit_replication":"https://pith.science/pith/I66YL2I4V6CBWELBONSITDV5W7/action/replication_record"}},"created_at":"2026-07-05T06:00:25.698990+00:00","updated_at":"2026-07-05T06:00:25.698990+00:00"}