{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YSKZ2H24LRJSQFVWFTDH3KBNBM","short_pith_number":"pith:YSKZ2H24","schema_version":"1.0","canonical_sha256":"c4959d1f5c5c532816b62cc67da82d0b372ea5c7c58db3043c93729adf32ed62","source":{"kind":"arxiv","id":"2305.15248","version":1},"attestation_state":"computed","paper":{"title":"Delving Deeper into Data Scaling in Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Jiashi Feng, Jun Hao Liew, Ming-Ming Cheng, Qibin Hou, Xiaojie Jin","submitted_at":"2023-05-24T15:33:46Z","abstract_excerpt":"Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods (e.g., MAE) for visual recognition. Unlike most previous works that depend on the widely-used ImageNet dataset, which is manually curated and object-centric, we take a step further and propose to investigate this problem in a more practical setting. Specifically, we utilize the web-collected Coyo-700M dataset. We randomly sample varying numbers of training ima"},"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":"2305.15248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T15:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"c1149ca9cf042ae8b2a486a99e5538edfd2997ca8403029ec270804d482e222c","abstract_canon_sha256":"eb18722aec011fc93524a50ede31c4b8ef92a9921d7e2aa64b417d30d11223d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:32.972916Z","signature_b64":"iEkhzSqMGZpraz0Q1ocQwR5orCZTa24zxtVDGQ/x9uEfX4WZucaTh0oJlo16Ggguqdz2jEYPGShU1iopnE+HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4959d1f5c5c532816b62cc67da82d0b372ea5c7c58db3043c93729adf32ed62","last_reissued_at":"2026-07-05T06:13:32.972442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:32.972442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving Deeper into Data Scaling in Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Ze Lu, Jiashi Feng, Jun Hao Liew, Ming-Ming Cheng, Qibin Hou, Xiaojie Jin","submitted_at":"2023-05-24T15:33:46Z","abstract_excerpt":"Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods (e.g., MAE) for visual recognition. Unlike most previous works that depend on the widely-used ImageNet dataset, which is manually curated and object-centric, we take a step further and propose to investigate this problem in a more practical setting. Specifically, we utilize the web-collected Coyo-700M dataset. We randomly sample varying numbers of training ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15248","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/2305.15248/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":"2305.15248","created_at":"2026-07-05T06:13:32.972500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15248v1","created_at":"2026-07-05T06:13:32.972500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15248","created_at":"2026-07-05T06:13:32.972500+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSKZ2H24LRJS","created_at":"2026-07-05T06:13:32.972500+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSKZ2H24LRJSQFVW","created_at":"2026-07-05T06:13:32.972500+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSKZ2H24","created_at":"2026-07-05T06:13:32.972500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03485","citing_title":"MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM","json":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM.json","graph_json":"https://pith.science/api/pith-number/YSKZ2H24LRJSQFVWFTDH3KBNBM/graph.json","events_json":"https://pith.science/api/pith-number/YSKZ2H24LRJSQFVWFTDH3KBNBM/events.json","paper":"https://pith.science/paper/YSKZ2H24"},"agent_actions":{"view_html":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM","download_json":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM.json","view_paper":"https://pith.science/paper/YSKZ2H24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15248&json=true","fetch_graph":"https://pith.science/api/pith-number/YSKZ2H24LRJSQFVWFTDH3KBNBM/graph.json","fetch_events":"https://pith.science/api/pith-number/YSKZ2H24LRJSQFVWFTDH3KBNBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM/action/storage_attestation","attest_author":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM/action/author_attestation","sign_citation":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM/action/citation_signature","submit_replication":"https://pith.science/pith/YSKZ2H24LRJSQFVWFTDH3KBNBM/action/replication_record"}},"created_at":"2026-07-05T06:13:32.972500+00:00","updated_at":"2026-07-05T06:13:32.972500+00:00"}