{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GFZBYZHCNLHSFRL2K2ZFL7OWG4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dda20bef4d98c17f05891ac87000ed6523d80819f78da0f6bb27495685a20ee7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T11:33:46Z","title_canon_sha256":"9de574aced47623ead960a4c9a94c9de7385becb5b691b8a7e90b322d06d7fae"},"schema_version":"1.0","source":{"id":"2408.03703","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03703","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03703v2","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03703","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"GFZBYZHCNLHS","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"GFZBYZHCNLHSFRL2","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"GFZBYZHC","created_at":"2026-07-05T09:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:061bbd08d8f5b6965ffd82624fcd96eed30d4385c43f23e17b96ff5b825f35d5","target":"graph","created_at":"2026-07-05T09:48:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.03703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Qian, Jenq-Neng Hwang, Lei Li, Tianfang Zhang, Wentao Liu, Xiangyang Ji, Yang Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T11:33:46Z","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03703","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3da5e430306f0bd0af931529b8e0c85ab3c9287b2c75a1a26510907636b5fc1","target":"record","created_at":"2026-07-05T09:48:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dda20bef4d98c17f05891ac87000ed6523d80819f78da0f6bb27495685a20ee7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T11:33:46Z","title_canon_sha256":"9de574aced47623ead960a4c9a94c9de7385becb5b691b8a7e90b322d06d7fae"},"schema_version":"1.0","source":{"id":"2408.03703","kind":"arxiv","version":2}},"canonical_sha256":"31721c64e26acf22c57a56b255fdd6370b07f8652bfcc832a7363fa731c4a6e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31721c64e26acf22c57a56b255fdd6370b07f8652bfcc832a7363fa731c4a6e8","first_computed_at":"2026-07-05T09:48:34.686441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:34.686441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hd96HLbutwUku4x1iBYlz3itQ+DaefYQr7N6dCVWiSJabV7he1I3YiEdOhjmb0j+G7kpvACkg1wIAoqiDEp3AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:34.686941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03703","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3da5e430306f0bd0af931529b8e0c85ab3c9287b2c75a1a26510907636b5fc1","sha256:061bbd08d8f5b6965ffd82624fcd96eed30d4385c43f23e17b96ff5b825f35d5"],"state_sha256":"f3ffd1a516107e3e6b734cc74053eae64af29e219f9b4ed4a4b4de16bda1383e"}