{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GFZBYZHCNLHSFRL2K2ZFL7OWG4","short_pith_number":"pith:GFZBYZHC","schema_version":"1.0","canonical_sha256":"31721c64e26acf22c57a56b255fdd6370b07f8652bfcc832a7363fa731c4a6e8","source":{"kind":"arxiv","id":"2408.03703","version":2},"attestation_state":"computed","paper":{"title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Qian, Jenq-Neng Hwang, Lei Li, Tianfang Zhang, Wentao Liu, Xiangyang Ji, Yang Zhou","submitted_at":"2024-08-07T11:33:46Z","abstract_excerpt":"Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on resource-constrained scenarios and real-time applications, such as mobile devices, although considerable efforts have been made in previous works. In this paper, we introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Firstly, we argue that the capability of token mix"},"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":"2408.03703","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T11:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"9de574aced47623ead960a4c9a94c9de7385becb5b691b8a7e90b322d06d7fae","abstract_canon_sha256":"dda20bef4d98c17f05891ac87000ed6523d80819f78da0f6bb27495685a20ee7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:34.686941Z","signature_b64":"Hd96HLbutwUku4x1iBYlz3itQ+DaefYQr7N6dCVWiSJabV7he1I3YiEdOhjmb0j+G7kpvACkg1wIAoqiDEp3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31721c64e26acf22c57a56b255fdd6370b07f8652bfcc832a7363fa731c4a6e8","last_reissued_at":"2026-07-05T09:48:34.686441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:34.686441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Qian, Jenq-Neng Hwang, Lei Li, Tianfang Zhang, Wentao Liu, Xiangyang Ji, Yang Zhou","submitted_at":"2024-08-07T11:33:46Z","abstract_excerpt":"Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on resource-constrained scenarios and real-time applications, such as mobile devices, although considerable efforts have been made in previous works. In this paper, we introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications. Firstly, we argue that the capability of token mix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03703","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/2408.03703/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":"2408.03703","created_at":"2026-07-05T09:48:34.686501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03703v2","created_at":"2026-07-05T09:48:34.686501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03703","created_at":"2026-07-05T09:48:34.686501+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFZBYZHCNLHS","created_at":"2026-07-05T09:48:34.686501+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFZBYZHCNLHSFRL2","created_at":"2026-07-05T09:48:34.686501+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFZBYZHC","created_at":"2026-07-05T09:48:34.686501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4","json":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4.json","graph_json":"https://pith.science/api/pith-number/GFZBYZHCNLHSFRL2K2ZFL7OWG4/graph.json","events_json":"https://pith.science/api/pith-number/GFZBYZHCNLHSFRL2K2ZFL7OWG4/events.json","paper":"https://pith.science/paper/GFZBYZHC"},"agent_actions":{"view_html":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4","download_json":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4.json","view_paper":"https://pith.science/paper/GFZBYZHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03703&json=true","fetch_graph":"https://pith.science/api/pith-number/GFZBYZHCNLHSFRL2K2ZFL7OWG4/graph.json","fetch_events":"https://pith.science/api/pith-number/GFZBYZHCNLHSFRL2K2ZFL7OWG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4/action/storage_attestation","attest_author":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4/action/author_attestation","sign_citation":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4/action/citation_signature","submit_replication":"https://pith.science/pith/GFZBYZHCNLHSFRL2K2ZFL7OWG4/action/replication_record"}},"created_at":"2026-07-05T09:48:34.686501+00:00","updated_at":"2026-07-05T09:48:34.686501+00:00"}