{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ITDG5B7B6ULKNEXTLYZZLG3PCT","short_pith_number":"pith:ITDG5B7B","schema_version":"1.0","canonical_sha256":"44c66e87e1f516a692f35e33959b6f14dbb0ed604bed2a968bcc7c4664170f4b","source":{"kind":"arxiv","id":"2301.01296","version":1},"attestation_state":"computed","paper":{"title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyun Wei, Han Hu, Sucheng Ren, Zheng Zhang","submitted_at":"2023-01-03T18:59:54Z","abstract_excerpt":"Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than"},"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":"2301.01296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"623b867f34399b640311a9bde600390bb6645a8c3972de0ebe66b39c3bb0354b","abstract_canon_sha256":"4611b883658be581a2c38d6a8a86780f32e22fc0376b33a305942d398736fd90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:22.871148Z","signature_b64":"VgMhtWo5mhcw/8h6m3Sg7wwExnGx0bwwrb/5Xsk7Hh5V3SsAPMKs9zZjccnwhRb8QZyKn5FJRyyZcN1KHpXcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44c66e87e1f516a692f35e33959b6f14dbb0ed604bed2a968bcc7c4664170f4b","last_reissued_at":"2026-07-05T05:30:22.870789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:22.870789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyun Wei, Han Hu, Sucheng Ren, Zheng Zhang","submitted_at":"2023-01-03T18:59:54Z","abstract_excerpt":"Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs). However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. In this paper, we explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones. We systematically study different options in the distillation framework, including distilling targets, losses, input, network regularization, sequential distillation, etc, revealing that: 1) Distilling token relations is more effective than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01296","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/2301.01296/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":"2301.01296","created_at":"2026-07-05T05:30:22.870846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01296v1","created_at":"2026-07-05T05:30:22.870846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01296","created_at":"2026-07-05T05:30:22.870846+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITDG5B7B6ULK","created_at":"2026-07-05T05:30:22.870846+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITDG5B7B6ULKNEXT","created_at":"2026-07-05T05:30:22.870846+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITDG5B7B","created_at":"2026-07-05T05:30:22.870846+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/ITDG5B7B6ULKNEXTLYZZLG3PCT","json":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT.json","graph_json":"https://pith.science/api/pith-number/ITDG5B7B6ULKNEXTLYZZLG3PCT/graph.json","events_json":"https://pith.science/api/pith-number/ITDG5B7B6ULKNEXTLYZZLG3PCT/events.json","paper":"https://pith.science/paper/ITDG5B7B"},"agent_actions":{"view_html":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT","download_json":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT.json","view_paper":"https://pith.science/paper/ITDG5B7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01296&json=true","fetch_graph":"https://pith.science/api/pith-number/ITDG5B7B6ULKNEXTLYZZLG3PCT/graph.json","fetch_events":"https://pith.science/api/pith-number/ITDG5B7B6ULKNEXTLYZZLG3PCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT/action/storage_attestation","attest_author":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT/action/author_attestation","sign_citation":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT/action/citation_signature","submit_replication":"https://pith.science/pith/ITDG5B7B6ULKNEXTLYZZLG3PCT/action/replication_record"}},"created_at":"2026-07-05T05:30:22.870846+00:00","updated_at":"2026-07-05T05:30:22.870846+00:00"}