{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZEM5FB3PQBSLZAL3JURK3NIWXY","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":"1377c996f95e7de14ab50fa72613475e423eeab494cc60f8f6957337c547bb25","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-01T17:56:09Z","title_canon_sha256":"0e3b988c4665b96319683e50d594ec19be166704da5a62a15bd10830403cbc82"},"schema_version":"1.0","source":{"id":"2107.00641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00641","created_at":"2026-07-05T02:54:26Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00641v1","created_at":"2026-07-05T02:54:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00641","created_at":"2026-07-05T02:54:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZEM5FB3PQBSL","created_at":"2026-07-05T02:54:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZEM5FB3PQBSLZAL3","created_at":"2026-07-05T02:54:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZEM5FB3P","created_at":"2026-07-05T02:54:26Z"}],"graph_snapshots":[{"event_id":"sha256:b15c4a218f25cebf6838161dae4c75f4387851cb9f146436e4eb6230c1a48df5","target":"graph","created_at":"2026-07-05T02:54:26Z","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/2107.00641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success. But it also brings challenges due to quadratic computational overhead, especially for the high-resolution vision tasks (e.g., object detection). In this paper, we present focal self-attention, a new mechanism that incorporates both fine-grained local and coarse-grained global interactions. Using this new mechanism, each token attends the closest surrounding ","authors_text":"Bin Xiao, Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lu Yuan, Pengchuan Zhang, Xiyang Dai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-01T17:56:09Z","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00641","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":"sha256:8af31d0723227be50bfc2a99af85b45ed089ebc8a1a5ed604c2d09404c9034fd","target":"record","created_at":"2026-07-05T02:54:26Z","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":"1377c996f95e7de14ab50fa72613475e423eeab494cc60f8f6957337c547bb25","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-01T17:56:09Z","title_canon_sha256":"0e3b988c4665b96319683e50d594ec19be166704da5a62a15bd10830403cbc82"},"schema_version":"1.0","source":{"id":"2107.00641","kind":"arxiv","version":1}},"canonical_sha256":"c919d2876f8064bc817b4d22adb516be3fd1aed40e6c9897bcbd098ea14ce8ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c919d2876f8064bc817b4d22adb516be3fd1aed40e6c9897bcbd098ea14ce8ed","first_computed_at":"2026-07-05T02:54:26.692960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:26.692960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4JIxISFB3iKZOSmYmEhb4rP9illBJfYGh0vD3f8783CTss8il91zAQ6lDbWjQZzGTD5wYN5UZv+jxnuPHvmaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:26.693397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8af31d0723227be50bfc2a99af85b45ed089ebc8a1a5ed604c2d09404c9034fd","sha256:b15c4a218f25cebf6838161dae4c75f4387851cb9f146436e4eb6230c1a48df5"],"state_sha256":"5f538b49480e2c2ce423ed1045c16ae260869b84a2479b36ef4c8761bc9ea1d7"}