{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FPIYUJ757H72ANK65MYM7SILM6","short_pith_number":"pith:FPIYUJ75","schema_version":"1.0","canonical_sha256":"2bd18a27fdf9ffa0355eeb30cfc90b67ad8eda5d439ac043a07fe24640548d2f","source":{"kind":"arxiv","id":"2207.10666","version":1},"attestation_state":"computed","paper":{"title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Houwen Peng, Jianlong Fu, Jinnian Zhang, Kan Wu, Lu Yuan, Mengchen Liu","submitted_at":"2022-07-21T17:59:56Z","abstract_excerpt":"Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices with limited resources. To alleviate this issue, we propose TinyViT, a new family of tiny and efficient small vision transformers pretrained on large-scale datasets with our proposed fast distillation framework. The central idea is to transfer knowledge from large pretrained models to small ones, while enabling small models to get the dividends of massive pretr"},"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":"2207.10666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"59654baa4b9b1a73d07186d8dc200cfb4dc445e592c0bd7cef3e6805ef8a287a","abstract_canon_sha256":"bc4967c1204c01a79d1680012e87897d999bf4798f62595f8d528433e70c75c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:28.266160Z","signature_b64":"Znax+ihZMI+77db92hvyuwzX9LNnqKbWFSaTa4NUQ3yz3+Qi38BIh8yDQTQZyMGfuvV1TfFC81Ms6oBAI0b2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd18a27fdf9ffa0355eeb30cfc90b67ad8eda5d439ac043a07fe24640548d2f","last_reissued_at":"2026-07-05T04:42:28.265641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:28.265641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Houwen Peng, Jianlong Fu, Jinnian Zhang, Kan Wu, Lu Yuan, Mengchen Liu","submitted_at":"2022-07-21T17:59:56Z","abstract_excerpt":"Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number of parameters, restricting their applicability on devices with limited resources. To alleviate this issue, we propose TinyViT, a new family of tiny and efficient small vision transformers pretrained on large-scale datasets with our proposed fast distillation framework. The central idea is to transfer knowledge from large pretrained models to small ones, while enabling small models to get the dividends of massive pretr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10666","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/2207.10666/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":"2207.10666","created_at":"2026-07-05T04:42:28.265709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10666v1","created_at":"2026-07-05T04:42:28.265709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10666","created_at":"2026-07-05T04:42:28.265709+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPIYUJ757H72","created_at":"2026-07-05T04:42:28.265709+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPIYUJ757H72ANK6","created_at":"2026-07-05T04:42:28.265709+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPIYUJ75","created_at":"2026-07-05T04:42:28.265709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14689","citing_title":"Are Candidate Models Really Needed for Active Learning?","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6","json":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6.json","graph_json":"https://pith.science/api/pith-number/FPIYUJ757H72ANK65MYM7SILM6/graph.json","events_json":"https://pith.science/api/pith-number/FPIYUJ757H72ANK65MYM7SILM6/events.json","paper":"https://pith.science/paper/FPIYUJ75"},"agent_actions":{"view_html":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6","download_json":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6.json","view_paper":"https://pith.science/paper/FPIYUJ75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10666&json=true","fetch_graph":"https://pith.science/api/pith-number/FPIYUJ757H72ANK65MYM7SILM6/graph.json","fetch_events":"https://pith.science/api/pith-number/FPIYUJ757H72ANK65MYM7SILM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6/action/storage_attestation","attest_author":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6/action/author_attestation","sign_citation":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6/action/citation_signature","submit_replication":"https://pith.science/pith/FPIYUJ757H72ANK65MYM7SILM6/action/replication_record"}},"created_at":"2026-07-05T04:42:28.265709+00:00","updated_at":"2026-07-05T04:42:28.265709+00:00"}