{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:APZ5DAWQZYNS63ORFF6UTPH5KV","short_pith_number":"pith:APZ5DAWQ","schema_version":"1.0","canonical_sha256":"03f3d182d0ce1b2f6dd1297d49bcfd5577dd7d5dae0583251550ac164173ff2b","source":{"kind":"arxiv","id":"2206.01191","version":5},"attestation_state":"computed","paper":{"title":"EfficientFormer: Vision Transformers at MobileNet Speed","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Yuan, Georgios Evangelidis, Jian Ren, Ju Hu, Sergey Tulyakov, Yang Wen, Yanyu Li, Yanzhi Wang","submitted_at":"2022-06-02T17:51:03Z","abstract_excerpt":"Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \\textit{e.g.}, attention mechanism, ViT-based models are generally times slower than lightweight convolutional networks. Therefore, the deployment of ViT for real-time applications is particularly challenging, especially on resource-constrained hardware such as mobile devices. Recent efforts try to reduce the computation complexity of ViT through network architecture search or hybrid design with Mobil"},"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":"2206.01191","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T17:51:03Z","cross_cats_sorted":[],"title_canon_sha256":"69b75697da610bd6c180461f45e5163436e20b3f1ecb9b84e73fc8687aa5faf0","abstract_canon_sha256":"3ac66832b7d8da458372fb1e977d0b56f05013ecbb59da0f155b7a5d218a86a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:06.027365Z","signature_b64":"4XPkJi8NboYNxJP9JHJTA9u3QMY3P95ewIMIizgecXtBkf+K9AI/vvpHEdaYSXAaiSnCfkaLqJ1qtNTH5XrBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f3d182d0ce1b2f6dd1297d49bcfd5577dd7d5dae0583251550ac164173ff2b","last_reissued_at":"2026-07-05T05:05:06.026929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:06.026929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientFormer: Vision Transformers at MobileNet Speed","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Yuan, Georgios Evangelidis, Jian Ren, Ju Hu, Sergey Tulyakov, Yang Wen, Yanyu Li, Yanzhi Wang","submitted_at":"2022-06-02T17:51:03Z","abstract_excerpt":"Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, \\textit{e.g.}, attention mechanism, ViT-based models are generally times slower than lightweight convolutional networks. Therefore, the deployment of ViT for real-time applications is particularly challenging, especially on resource-constrained hardware such as mobile devices. Recent efforts try to reduce the computation complexity of ViT through network architecture search or hybrid design with Mobil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01191","kind":"arxiv","version":5},"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/2206.01191/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":"2206.01191","created_at":"2026-07-05T05:05:06.026987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01191v5","created_at":"2026-07-05T05:05:06.026987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01191","created_at":"2026-07-05T05:05:06.026987+00:00"},{"alias_kind":"pith_short_12","alias_value":"APZ5DAWQZYNS","created_at":"2026-07-05T05:05:06.026987+00:00"},{"alias_kind":"pith_short_16","alias_value":"APZ5DAWQZYNS63OR","created_at":"2026-07-05T05:05:06.026987+00:00"},{"alias_kind":"pith_short_8","alias_value":"APZ5DAWQ","created_at":"2026-07-05T05:05:06.026987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV","json":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV.json","graph_json":"https://pith.science/api/pith-number/APZ5DAWQZYNS63ORFF6UTPH5KV/graph.json","events_json":"https://pith.science/api/pith-number/APZ5DAWQZYNS63ORFF6UTPH5KV/events.json","paper":"https://pith.science/paper/APZ5DAWQ"},"agent_actions":{"view_html":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV","download_json":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV.json","view_paper":"https://pith.science/paper/APZ5DAWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01191&json=true","fetch_graph":"https://pith.science/api/pith-number/APZ5DAWQZYNS63ORFF6UTPH5KV/graph.json","fetch_events":"https://pith.science/api/pith-number/APZ5DAWQZYNS63ORFF6UTPH5KV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV/action/storage_attestation","attest_author":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV/action/author_attestation","sign_citation":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV/action/citation_signature","submit_replication":"https://pith.science/pith/APZ5DAWQZYNS63ORFF6UTPH5KV/action/replication_record"}},"created_at":"2026-07-05T05:05:06.026987+00:00","updated_at":"2026-07-05T05:05:06.026987+00:00"}