{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZOMT26CVHMGBDEJIN354AMIN62","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":"095286368bdb60d6306f5e7efc36ca48bf1557d1321ba543857fb3e8bbcb085e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-10T02:34:55Z","title_canon_sha256":"ac68e0972879a14038bed5c07859246f91a5804fc3f976e9bc43ea123aebeb7b"},"schema_version":"1.0","source":{"id":"2107.04735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04735","created_at":"2026-07-05T02:56:42Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04735v1","created_at":"2026-07-05T02:56:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04735","created_at":"2026-07-05T02:56:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZOMT26CVHMGB","created_at":"2026-07-05T02:56:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZOMT26CVHMGBDEJI","created_at":"2026-07-05T02:56:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZOMT26CV","created_at":"2026-07-05T02:56:42Z"}],"graph_snapshots":[{"event_id":"sha256:5186fa7851909192dac6ab902414dd0bae0daa55486ff497079a21d76e8820d2","target":"graph","created_at":"2026-07-05T02:56:42Z","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/2107.04735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where self-attentions are only computed within local windows. This design significantly improves the efficiency but lacks global feature reasoning in early stages. In this work, we design a multi-path structure of the Transformer, which enables local-to-global reasoning at multiple granularities in each stage. The proposed framework is computationally efficient and highly effective. Wi","authors_text":"Jinpeng Li, Ling Shao, Shengcai Liao, Xiaokang Yang, Yichao Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-10T02:34:55Z","title":"Local-to-Global Self-Attention in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04735","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:a5ebf5d1c188067c134388c4babc6304e3722872ee20a27e28fcd6ec775104b4","target":"record","created_at":"2026-07-05T02:56:42Z","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":"095286368bdb60d6306f5e7efc36ca48bf1557d1321ba543857fb3e8bbcb085e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-10T02:34:55Z","title_canon_sha256":"ac68e0972879a14038bed5c07859246f91a5804fc3f976e9bc43ea123aebeb7b"},"schema_version":"1.0","source":{"id":"2107.04735","kind":"arxiv","version":1}},"canonical_sha256":"cb993d78553b0c1191286efbc0310df6b3f1a21d9eed28abe6cdf30bd8dd1b39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb993d78553b0c1191286efbc0310df6b3f1a21d9eed28abe6cdf30bd8dd1b39","first_computed_at":"2026-07-05T02:56:42.336701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:42.336701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MN6vLSbPVpyRr+WkcSbgOvSXtVetgsqAsPdzi6kj/6q3mZ/dn8ixgqOBBZTXh3zSGM7ldW8EQi1wXfJT/aI8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:42.337160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.04735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5ebf5d1c188067c134388c4babc6304e3722872ee20a27e28fcd6ec775104b4","sha256:5186fa7851909192dac6ab902414dd0bae0daa55486ff497079a21d76e8820d2"],"state_sha256":"ce31f733833f423e659af385462da742398f381fc832933bed48d37076da89c7"}