{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DLECX7IOWSM7DPKCDJDTIVQQJH","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":"4a06f19901551ec3238ab2000b740468a2ebef940b81b641ce4ed032cf6c56b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:59:41Z","title_canon_sha256":"20abf59cfb3e2ec71db3e602a2d34570576787c717de6e67d3516d993efcc509"},"schema_version":"1.0","source":{"id":"2305.07027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07027","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07027v1","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07027","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"DLECX7IOWSM7","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"DLECX7IOWSM7DPKC","created_at":"2026-07-05T06:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"DLECX7IO","created_at":"2026-07-05T06:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:7f519c14c8e94761da357f61a5f15e859a64d3d8389f0d70c7b7ae565d1293c4","target":"graph","created_at":"2026-07-05T06:09:18Z","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/2305.07027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named EfficientViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between ef","authors_text":"Han Hu, Houwen Peng, Ningxin Zheng, Xinyu Liu, Yixuan Yuan, Yuqing Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:59:41Z","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07027","kind":"arxiv","version":1},"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":"sha256:1466fef7ebb75bf6eb7efe20decdd62ada847abb2215a1baf5d3422749ed0c13","target":"record","created_at":"2026-07-05T06:09:18Z","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":"4a06f19901551ec3238ab2000b740468a2ebef940b81b641ce4ed032cf6c56b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:59:41Z","title_canon_sha256":"20abf59cfb3e2ec71db3e602a2d34570576787c717de6e67d3516d993efcc509"},"schema_version":"1.0","source":{"id":"2305.07027","kind":"arxiv","version":1}},"canonical_sha256":"1ac82bfd0eb499f1bd421a4734561049e7fc2a46a952609a309a7c5606c9afda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ac82bfd0eb499f1bd421a4734561049e7fc2a46a952609a309a7c5606c9afda","first_computed_at":"2026-07-05T06:09:18.736649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:18.736649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4g9wwbJxj3tnYmG0rrss2j2Xzp+VZING5GgIwvjKDAX+XetIPAx5oEVwp4e4mER60yV/ceNod5owYrLjNAzYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:18.737155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1466fef7ebb75bf6eb7efe20decdd62ada847abb2215a1baf5d3422749ed0c13","sha256:7f519c14c8e94761da357f61a5f15e859a64d3d8389f0d70c7b7ae565d1293c4"],"state_sha256":"e2702959162bbbcd2ff8067ec8f781df66d8e506bf9b300d386e573333a91e12"}