{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CKVMSN2SFOGSBIBOV6LQ2FFDVJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"121951cdc94121689b1ba15bfcdb6b9f86f33438027c07b298045b440c672561","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:14:44Z","title_canon_sha256":"84e96e0856aeb08095939c89f7b3759bbb22659c64b13d313056076aede41917"},"schema_version":"1.0","source":{"id":"2404.12210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12210","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12210v2","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12210","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"CKVMSN2SFOGS","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"CKVMSN2SFOGSBIBO","created_at":"2026-07-05T08:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"CKVMSN2S","created_at":"2026-07-05T08:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:a061d8efe221e744028e8b01e3f758904abc9e0ed493a72cf5d98bed827da75f","target":"graph","created_at":"2026-07-05T08:23:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.12210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Congxuan Zhang, Jin Gao, Liang Li, Shaoru Wang, Shubo Lin, Weiming Hu, Xiaoqin Zhang, Yizheng Wang, Yutong Kou, Zeming Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:14:44Z","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12210","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08d07885de497c624a85e0ebe84dfc24ab6d86182111252f55265f303ce6de8f","target":"record","created_at":"2026-07-05T08:23:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"121951cdc94121689b1ba15bfcdb6b9f86f33438027c07b298045b440c672561","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T14:14:44Z","title_canon_sha256":"84e96e0856aeb08095939c89f7b3759bbb22659c64b13d313056076aede41917"},"schema_version":"1.0","source":{"id":"2404.12210","kind":"arxiv","version":2}},"canonical_sha256":"12aac937522b8d20a02eaf970d14a3aa628df33dc4f5295c1ed04945a8244364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12aac937522b8d20a02eaf970d14a3aa628df33dc4f5295c1ed04945a8244364","first_computed_at":"2026-07-05T08:23:21.427260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:21.427260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YShI8tCXMqGna8YBX2JPqJShmJKgnIZ4G+qAWA624ht+mE7cbT436fnnPSut/uWTBCRBRtRlKAyuG2q8LMXAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:21.427719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08d07885de497c624a85e0ebe84dfc24ab6d86182111252f55265f303ce6de8f","sha256:a061d8efe221e744028e8b01e3f758904abc9e0ed493a72cf5d98bed827da75f"],"state_sha256":"49e727639cd2921dd9ed54636ba3626dd8f679c86675ecbd6c1bda0d9cd751d7"}