{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XV3A4YUWWDFOO3GADMLLAMTXHZ","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":"e4e46c4eb1282fd88fe293fb0c93533a2595cbc6c8f1dd5b21bd3ececa1ca301","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T15:42:31Z","title_canon_sha256":"38e1568655133511b577a3054a8d96db38177b866490964897ea79091480c2b3"},"schema_version":"1.0","source":{"id":"2104.13840","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13840","created_at":"2026-07-05T03:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13840v4","created_at":"2026-07-05T03:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13840","created_at":"2026-07-05T03:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"XV3A4YUWWDFO","created_at":"2026-07-05T03:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"XV3A4YUWWDFOO3GA","created_at":"2026-07-05T03:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"XV3A4YUW","created_at":"2026-07-05T03:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:ea5d07defde3e33945202caba92589d0cb646c74bed33e7705b419dd715e2044","target":"graph","created_at":"2026-07-05T03:18:40Z","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/2104.13840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design of the spatial attention and demonstrate that a carefully-devised yet simple spatial attention mechanism performs favourably against the state-of-the-art schemes. As a result, we propose two vision transformer architectures, namely, Twins-PCPVT and Twins-SVT. Our proposed architectures are highly-efficient and easy to implement, only involving matrix multipli","authors_text":"Bo Zhang, Chunhua Shen, Haibing Ren, Huaxia Xia, Xiangxiang Chu, Xiaolin Wei, Yuqing Wang, Zhi Tian","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T15:42:31Z","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13840","kind":"arxiv","version":4},"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:c43ac5e9f75de7a235c39c045d2504a04859d770ae502cb5f1f6bff63396569f","target":"record","created_at":"2026-07-05T03:18:40Z","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":"e4e46c4eb1282fd88fe293fb0c93533a2595cbc6c8f1dd5b21bd3ececa1ca301","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T15:42:31Z","title_canon_sha256":"38e1568655133511b577a3054a8d96db38177b866490964897ea79091480c2b3"},"schema_version":"1.0","source":{"id":"2104.13840","kind":"arxiv","version":4}},"canonical_sha256":"bd760e6296b0cae76cc01b16b032773e7020efaf655e18f8d4f5f2c505a52fbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd760e6296b0cae76cc01b16b032773e7020efaf655e18f8d4f5f2c505a52fbf","first_computed_at":"2026-07-05T03:18:40.513088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:40.513088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LBT2jqCTAxHSE/fO0sFowWMHq5m4X3WL9RYt/ck5yjk16fHfkXaT6JlRLy1uCtb+kShq7U2HOtPen/wR/u4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:40.513491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.13840","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c43ac5e9f75de7a235c39c045d2504a04859d770ae502cb5f1f6bff63396569f","sha256:ea5d07defde3e33945202caba92589d0cb646c74bed33e7705b419dd715e2044"],"state_sha256":"6d2b7236c9a3c2946e575a8f32c3eae2197c0f11b83400c4094005d4b567b996"}