{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CLXB4YQIHNV2VISTPUHPQKM3S2","short_pith_number":"pith:CLXB4YQI","schema_version":"1.0","canonical_sha256":"12ee1e62083b6baaa2537d0ef8299b96a8be9fb829d401044816740bf0abbbfc","source":{"kind":"arxiv","id":"2104.01136","version":2},"attestation_state":"computed","paper":{"title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alaaeldin El-Nouby, Armand Joulin, Ben Graham, Herv\\'e J\\'egou, Hugo Touvron, Matthijs Douze, Pierre Stock","submitted_at":"2021-04-02T16:29:57Z","abstract_excerpt":"We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers. As a result, we propose LeVIT: a hybrid neural"},"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":"2104.01136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T16:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"1f128d021a3817548c9e5741aabf8d6f7885107d706dc05e775c072c041ddbb6","abstract_canon_sha256":"f0915907ad9ae47e7638a6c901f6dbcb610871de774c59fb3e40ae5115a6615f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:09.546520Z","signature_b64":"3Ze2JABYz/sKmPkvLPlPW/BIZHyaAMPbDVCZmWnXuskwUDcgtgR6y/DfTmAzFroreD76i2pqjSe+NFlYiGM3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ee1e62083b6baaa2537d0ef8299b96a8be9fb829d401044816740bf0abbbfc","last_reissued_at":"2026-07-05T02:38:09.546071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:09.546071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alaaeldin El-Nouby, Armand Joulin, Ben Graham, Herv\\'e J\\'egou, Hugo Touvron, Matthijs Douze, Pierre Stock","submitted_at":"2021-04-02T16:29:57Z","abstract_excerpt":"We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers. As a result, we propose LeVIT: a hybrid neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01136","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/2104.01136/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":"2104.01136","created_at":"2026-07-05T02:38:09.546130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01136v2","created_at":"2026-07-05T02:38:09.546130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01136","created_at":"2026-07-05T02:38:09.546130+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLXB4YQIHNV2","created_at":"2026-07-05T02:38:09.546130+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLXB4YQIHNV2VIST","created_at":"2026-07-05T02:38:09.546130+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLXB4YQI","created_at":"2026-07-05T02:38:09.546130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2110.02178","citing_title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2","json":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2.json","graph_json":"https://pith.science/api/pith-number/CLXB4YQIHNV2VISTPUHPQKM3S2/graph.json","events_json":"https://pith.science/api/pith-number/CLXB4YQIHNV2VISTPUHPQKM3S2/events.json","paper":"https://pith.science/paper/CLXB4YQI"},"agent_actions":{"view_html":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2","download_json":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2.json","view_paper":"https://pith.science/paper/CLXB4YQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01136&json=true","fetch_graph":"https://pith.science/api/pith-number/CLXB4YQIHNV2VISTPUHPQKM3S2/graph.json","fetch_events":"https://pith.science/api/pith-number/CLXB4YQIHNV2VISTPUHPQKM3S2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2/action/storage_attestation","attest_author":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2/action/author_attestation","sign_citation":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2/action/citation_signature","submit_replication":"https://pith.science/pith/CLXB4YQIHNV2VISTPUHPQKM3S2/action/replication_record"}},"created_at":"2026-07-05T02:38:09.546130+00:00","updated_at":"2026-07-05T02:38:09.546130+00:00"}