{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CYN6Q4ZNPBWGFUQQQ3ZX2L7LWF","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":"e01e9b313cbed46ec908b24337bb82632ce3f1db08373a83c0bf23807a38de33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T14:38:32Z","title_canon_sha256":"94a562a6737f7c5803699228410a52faf9c58c1235d3c5be23c85e856516cfa1"},"schema_version":"1.0","source":{"id":"2106.05786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05786","created_at":"2026-07-05T02:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05786v1","created_at":"2026-07-05T02:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05786","created_at":"2026-07-05T02:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"CYN6Q4ZNPBWG","created_at":"2026-07-05T02:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"CYN6Q4ZNPBWGFUQQ","created_at":"2026-07-05T02:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"CYN6Q4ZN","created_at":"2026-07-05T02:48:13Z"}],"graph_snapshots":[{"event_id":"sha256:55c577dec17f454d82d39867f0f18be2bfe1b935f5a9213fbc5c2f8bb7b3a721","target":"graph","created_at":"2026-07-05T02:48:13Z","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/2106.05786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer after the tokenization of the image is vast(e.g., ViT), which bottlenecks model training and inference. In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided fro","authors_text":"Dong Shen, Fan Yang, Hezheng Lin, Qing Song, Wei Yuan, Xiangyu Wu, Xing Cheng, Zhongyuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T14:38:32Z","title":"CAT: Cross Attention in Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05786","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":"sha256:84e8a5d4f54a911f83cc82280c7d76673d42475ff47896b630cc1add34e40b93","target":"record","created_at":"2026-07-05T02:48:13Z","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":"e01e9b313cbed46ec908b24337bb82632ce3f1db08373a83c0bf23807a38de33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-10T14:38:32Z","title_canon_sha256":"94a562a6737f7c5803699228410a52faf9c58c1235d3c5be23c85e856516cfa1"},"schema_version":"1.0","source":{"id":"2106.05786","kind":"arxiv","version":1}},"canonical_sha256":"161be8732d786c62d21086f37d2febb15a1063e0593be18ee2c57efe215f2cde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"161be8732d786c62d21086f37d2febb15a1063e0593be18ee2c57efe215f2cde","first_computed_at":"2026-07-05T02:48:13.055857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:13.055857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ncLsHn75VHsuKSY7Y47+SK0N/7x7t4RZzCiIOTsKylrrtLr8KJGxASMUwWdSDrH+ZmtMeh0T9n3wfwdqYianDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:13.056393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e8a5d4f54a911f83cc82280c7d76673d42475ff47896b630cc1add34e40b93","sha256:55c577dec17f454d82d39867f0f18be2bfe1b935f5a9213fbc5c2f8bb7b3a721"],"state_sha256":"1a284c3ca7f983796559b2e59a5ce3aa2d3e1f9e8b4fbde2ebd14366b8fb758c"}