{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ATCOQWHT463PBJM25P3AWNRVQ6","short_pith_number":"pith:ATCOQWHT","schema_version":"1.0","canonical_sha256":"04c4e858f3e7b6f0a59aebf60b363587a28775fe0c8fcb9c7f87bf23641bc734","source":{"kind":"arxiv","id":"2107.00652","version":3},"attestation_state":"computed","paper":{"title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Jianmin Bao, Lu Yuan, Nenghai Yu, Weiming Zhang, Xiaoyi Dong","submitted_at":"2021-07-01T17:59:56Z","abstract_excerpt":"We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local self-attention often limits the field of interactions of each token. To address this issue, we develop the Cross-Shaped Window self-attention mechanism for computing self-attention in the horizontal and vertical stripes in parallel that form a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. We provide a mat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.00652","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-01T17:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b067c4ed2d506af6818537c7c28f768fb1399d1a4535add184b40130bdd85642","abstract_canon_sha256":"63c91ba034417d3bb8937a03e916c368e010c674d2a83659aa9122008724bf14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:59.373714Z","signature_b64":"q24SP4xrp8FZ9rVNKuj+a5Kl0dxf36Mo4CCFE0fAx29UomHwUHCqHR4LT6A1DfddbwvpBNqbk7DFTG/n54uWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04c4e858f3e7b6f0a59aebf60b363587a28775fe0c8fcb9c7f87bf23641bc734","last_reissued_at":"2026-07-05T03:46:59.373208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:59.373208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Jianmin Bao, Lu Yuan, Nenghai Yu, Weiming Zhang, Xiaoyi Dong","submitted_at":"2021-07-01T17:59:56Z","abstract_excerpt":"We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local self-attention often limits the field of interactions of each token. To address this issue, we develop the Cross-Shaped Window self-attention mechanism for computing self-attention in the horizontal and vertical stripes in parallel that form a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. We provide a mat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00652","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.00652/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.00652","created_at":"2026-07-05T03:46:59.373270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00652v3","created_at":"2026-07-05T03:46:59.373270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00652","created_at":"2026-07-05T03:46:59.373270+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATCOQWHT463P","created_at":"2026-07-05T03:46:59.373270+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATCOQWHT463PBJM2","created_at":"2026-07-05T03:46:59.373270+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATCOQWHT","created_at":"2026-07-05T03:46:59.373270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2111.11432","citing_title":"Florence: A New Foundation Model for Computer Vision","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6","json":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6.json","graph_json":"https://pith.science/api/pith-number/ATCOQWHT463PBJM25P3AWNRVQ6/graph.json","events_json":"https://pith.science/api/pith-number/ATCOQWHT463PBJM25P3AWNRVQ6/events.json","paper":"https://pith.science/paper/ATCOQWHT"},"agent_actions":{"view_html":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6","download_json":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6.json","view_paper":"https://pith.science/paper/ATCOQWHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00652&json=true","fetch_graph":"https://pith.science/api/pith-number/ATCOQWHT463PBJM25P3AWNRVQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ATCOQWHT463PBJM25P3AWNRVQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6/action/storage_attestation","attest_author":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6/action/author_attestation","sign_citation":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6/action/citation_signature","submit_replication":"https://pith.science/pith/ATCOQWHT463PBJM25P3AWNRVQ6/action/replication_record"}},"created_at":"2026-07-05T03:46:59.373270+00:00","updated_at":"2026-07-05T03:46:59.373270+00:00"}