{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z72CXEUDUO2COXSS2ORQP6GUHS","short_pith_number":"pith:Z72CXEUD","schema_version":"1.0","canonical_sha256":"cff42b9283a3b4275e52d3a307f8d43c932132556c90310b78512e0acace5127","source":{"kind":"arxiv","id":"2206.10589","version":3},"attestation_state":"computed","paper":{"title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Hisham Cholakkal, Muhammad Maaz, Rao Muhammad Anwer, Salman Khan, Syed Waqas Zamir","submitted_at":"2022-06-21T17:59:56Z","abstract_excerpt":"In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (STDA) encoder that splits inp"},"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":"2206.10589","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-21T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"970a8cf5e32ccbcbaf63c3d22d704412bdde5de8516abc7c60a8b636d46e67fd","abstract_canon_sha256":"25e970710e6735cf60b36d2c3cbdfc5840d767698e957bbf4c7bb771fefb2c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:19.432272Z","signature_b64":"RIft1BlHeGc/4QauRP+oZNlaWwWG0RgQSZDRUkPA3zf/thf5D7I99q6x+NmX5uYO2WFW/RFaLpcloBjvwSt+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff42b9283a3b4275e52d3a307f8d43c932132556c90310b78512e0acace5127","last_reissued_at":"2026-07-05T05:09:19.431833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:19.431833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Hisham Cholakkal, Muhammad Maaz, Rao Muhammad Anwer, Salman Khan, Syed Waqas Zamir","submitted_at":"2022-06-21T17:59:56Z","abstract_excerpt":"In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (STDA) encoder that splits inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10589","kind":"arxiv","version":3},"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/2206.10589/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":"2206.10589","created_at":"2026-07-05T05:09:19.431892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10589v3","created_at":"2026-07-05T05:09:19.431892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10589","created_at":"2026-07-05T05:09:19.431892+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z72CXEUDUO2C","created_at":"2026-07-05T05:09:19.431892+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z72CXEUDUO2COXSS","created_at":"2026-07-05T05:09:19.431892+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z72CXEUD","created_at":"2026-07-05T05:09:19.431892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS","json":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS.json","graph_json":"https://pith.science/api/pith-number/Z72CXEUDUO2COXSS2ORQP6GUHS/graph.json","events_json":"https://pith.science/api/pith-number/Z72CXEUDUO2COXSS2ORQP6GUHS/events.json","paper":"https://pith.science/paper/Z72CXEUD"},"agent_actions":{"view_html":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS","download_json":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS.json","view_paper":"https://pith.science/paper/Z72CXEUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10589&json=true","fetch_graph":"https://pith.science/api/pith-number/Z72CXEUDUO2COXSS2ORQP6GUHS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z72CXEUDUO2COXSS2ORQP6GUHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS/action/storage_attestation","attest_author":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS/action/author_attestation","sign_citation":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS/action/citation_signature","submit_replication":"https://pith.science/pith/Z72CXEUDUO2COXSS2ORQP6GUHS/action/replication_record"}},"created_at":"2026-07-05T05:09:19.431892+00:00","updated_at":"2026-07-05T05:09:19.431892+00:00"}