{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:47B6SFVL5GWQVS37XBYRUO3IST","short_pith_number":"pith:47B6SFVL","schema_version":"1.0","canonical_sha256":"e7c3e916abe9ad0acb7fb8711a3b6894f9b99a4b88b5f61fea16f4e6acbe6d25","source":{"kind":"arxiv","id":"2303.15105","version":1},"attestation_state":"computed","paper":{"title":"Vision Transformer with Quadrangle Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jing Zhang, Qiming Zhang, Yufei Xu","submitted_at":"2023-03-27T11:13:50Z","abstract_excerpt":"Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibility of transformers to adapt to objects of varying sizes, shapes, and orientations. To address this issue, we propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation 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":"2303.15105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-27T11:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"4dc1bbd9230f90c1abf3c35ed473e31888a0683bad40795f843607a07d010e31","abstract_canon_sha256":"a805afed2f5ef4eb15793be4cb7a93e8ca0f4c9cc9611f8598a8803c312b02df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:01.060122Z","signature_b64":"eAY0ATPqybdJAp8CMziRPAhiuKaRjG+4PBiejkqOEH0WvhGW8U0B/DiAGQ8jcDOG0uRhEYE77gWrJxiN3kD4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c3e916abe9ad0acb7fb8711a3b6894f9b99a4b88b5f61fea16f4e6acbe6d25","last_reissued_at":"2026-07-05T05:55:01.059782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:01.059782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Transformer with Quadrangle Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jing Zhang, Qiming Zhang, Yufei Xu","submitted_at":"2023-03-27T11:13:50Z","abstract_excerpt":"Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibility of transformers to adapt to objects of varying sizes, shapes, and orientations. To address this issue, we propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation mat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15105","kind":"arxiv","version":1},"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/2303.15105/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":"2303.15105","created_at":"2026-07-05T05:55:01.059838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.15105v1","created_at":"2026-07-05T05:55:01.059838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15105","created_at":"2026-07-05T05:55:01.059838+00:00"},{"alias_kind":"pith_short_12","alias_value":"47B6SFVL5GWQ","created_at":"2026-07-05T05:55:01.059838+00:00"},{"alias_kind":"pith_short_16","alias_value":"47B6SFVL5GWQVS37","created_at":"2026-07-05T05:55:01.059838+00:00"},{"alias_kind":"pith_short_8","alias_value":"47B6SFVL","created_at":"2026-07-05T05:55:01.059838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.05067","citing_title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15994","citing_title":"ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST","json":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST.json","graph_json":"https://pith.science/api/pith-number/47B6SFVL5GWQVS37XBYRUO3IST/graph.json","events_json":"https://pith.science/api/pith-number/47B6SFVL5GWQVS37XBYRUO3IST/events.json","paper":"https://pith.science/paper/47B6SFVL"},"agent_actions":{"view_html":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST","download_json":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST.json","view_paper":"https://pith.science/paper/47B6SFVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.15105&json=true","fetch_graph":"https://pith.science/api/pith-number/47B6SFVL5GWQVS37XBYRUO3IST/graph.json","fetch_events":"https://pith.science/api/pith-number/47B6SFVL5GWQVS37XBYRUO3IST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST/action/storage_attestation","attest_author":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST/action/author_attestation","sign_citation":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST/action/citation_signature","submit_replication":"https://pith.science/pith/47B6SFVL5GWQVS37XBYRUO3IST/action/replication_record"}},"created_at":"2026-07-05T05:55:01.059838+00:00","updated_at":"2026-07-05T05:55:01.059838+00:00"}