{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CKVMSN2SFOGSBIBOV6LQ2FFDVJ","short_pith_number":"pith:CKVMSN2S","schema_version":"1.0","canonical_sha256":"12aac937522b8d20a02eaf970d14a3aa628df33dc4f5295c1ed04945a8244364","source":{"kind":"arxiv","id":"2404.12210","version":2},"attestation_state":"computed","paper":{"title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congxuan Zhang, Jin Gao, Liang Li, Shaoru Wang, Shubo Lin, Weiming Hu, Xiaoqin Zhang, Yizheng Wang, Yutong Kou, Zeming Li","submitted_at":"2024-04-18T14:14:44Z","abstract_excerpt":"Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \\textit{extremely simple} lightweight ViTs' fine-tuning performance can also benefit from this pre-training paradigm, which is considerably less studied yet in contrast to the well-established lightweight architecture design methodology. We use an observation-analysis-solution flow for our study. We first systematically observe different behaviors among the evaluated pre-training me"},"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":"2404.12210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"84e96e0856aeb08095939c89f7b3759bbb22659c64b13d313056076aede41917","abstract_canon_sha256":"121951cdc94121689b1ba15bfcdb6b9f86f33438027c07b298045b440c672561"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:21.427719Z","signature_b64":"YShI8tCXMqGna8YBX2JPqJShmJKgnIZ4G+qAWA624ht+mE7cbT436fnnPSut/uWTBCRBRtRlKAyuG2q8LMXAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12aac937522b8d20a02eaf970d14a3aa628df33dc4f5295c1ed04945a8244364","last_reissued_at":"2026-07-05T08:23:21.427260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:21.427260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congxuan Zhang, Jin Gao, Liang Li, Shaoru Wang, Shubo Lin, Weiming Hu, Xiaoqin Zhang, Yizheng Wang, Yutong Kou, Zeming Li","submitted_at":"2024-04-18T14:14:44Z","abstract_excerpt":"Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \\textit{extremely simple} lightweight ViTs' fine-tuning performance can also benefit from this pre-training paradigm, which is considerably less studied yet in contrast to the well-established lightweight architecture design methodology. We use an observation-analysis-solution flow for our study. We first systematically observe different behaviors among the evaluated pre-training me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12210","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/2404.12210/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":"2404.12210","created_at":"2026-07-05T08:23:21.427320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12210v2","created_at":"2026-07-05T08:23:21.427320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12210","created_at":"2026-07-05T08:23:21.427320+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKVMSN2SFOGS","created_at":"2026-07-05T08:23:21.427320+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKVMSN2SFOGSBIBO","created_at":"2026-07-05T08:23:21.427320+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKVMSN2S","created_at":"2026-07-05T08:23:21.427320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.07442","citing_title":"Self-Supervised Learning for Real-World Object Detection: a Survey","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ","json":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ.json","graph_json":"https://pith.science/api/pith-number/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/graph.json","events_json":"https://pith.science/api/pith-number/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/events.json","paper":"https://pith.science/paper/CKVMSN2S"},"agent_actions":{"view_html":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ","download_json":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ.json","view_paper":"https://pith.science/paper/CKVMSN2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12210&json=true","fetch_graph":"https://pith.science/api/pith-number/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/action/storage_attestation","attest_author":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/action/author_attestation","sign_citation":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/action/citation_signature","submit_replication":"https://pith.science/pith/CKVMSN2SFOGSBIBOV6LQ2FFDVJ/action/replication_record"}},"created_at":"2026-07-05T08:23:21.427320+00:00","updated_at":"2026-07-05T08:23:21.427320+00:00"}