{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XRPWNMMGDFMVSEPEPJBMFJGD5U","short_pith_number":"pith:XRPWNMMG","schema_version":"1.0","canonical_sha256":"bc5f66b18619595911e47a42c2a4c3ed3815c6b1357efd0c0d794ecec1d3a122","source":{"kind":"arxiv","id":"2207.04976","version":2},"attestation_state":"computed","paper":{"title":"Dual Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Xiao-Ping Zhang, Yehao Li, Yingwei Pan, Yu Wang","submitted_at":"2022-07-11T16:03:44Z","abstract_excerpt":"Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each incurs a much smaller computational complexity. However, regional information is typically only achieved at the expense of undesirable information lost owing to down-sampling. In this paper, we propose a novel Transformer architecture that aims to mitigate the cost issue, named Dual Vision Transformer (Dual-ViT). The new architecture incorporates a critical"},"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":"2207.04976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-11T16:03:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eac103ce736e651f088110cf50c0f752dcdcd056c42609c5668caebf0252b5ab","abstract_canon_sha256":"8ab25d1b0547fc4e2e0061d1988f73de01ed52ec364517ee491dc75bd7bd23ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:40.620717Z","signature_b64":"5WY02cFzCIPr3xFi0VqgpSiSxh+Aht9DNvDU5ySlHF1kVdb9zP/Ifjazw76OnQeUmyYW4VYXVbS29uZEjIW5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc5f66b18619595911e47a42c2a4c3ed3815c6b1357efd0c0d794ecec1d3a122","last_reissued_at":"2026-07-05T04:39:40.620246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:40.620246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Xiao-Ping Zhang, Yehao Li, Yingwei Pan, Yu Wang","submitted_at":"2022-07-11T16:03:44Z","abstract_excerpt":"Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each incurs a much smaller computational complexity. However, regional information is typically only achieved at the expense of undesirable information lost owing to down-sampling. In this paper, we propose a novel Transformer architecture that aims to mitigate the cost issue, named Dual Vision Transformer (Dual-ViT). The new architecture incorporates a critical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04976","kind":"arxiv","version":2},"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/2207.04976/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":"2207.04976","created_at":"2026-07-05T04:39:40.620305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04976v2","created_at":"2026-07-05T04:39:40.620305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04976","created_at":"2026-07-05T04:39:40.620305+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRPWNMMGDFMV","created_at":"2026-07-05T04:39:40.620305+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRPWNMMGDFMVSEPE","created_at":"2026-07-05T04:39:40.620305+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRPWNMMG","created_at":"2026-07-05T04:39:40.620305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U","json":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U.json","graph_json":"https://pith.science/api/pith-number/XRPWNMMGDFMVSEPEPJBMFJGD5U/graph.json","events_json":"https://pith.science/api/pith-number/XRPWNMMGDFMVSEPEPJBMFJGD5U/events.json","paper":"https://pith.science/paper/XRPWNMMG"},"agent_actions":{"view_html":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U","download_json":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U.json","view_paper":"https://pith.science/paper/XRPWNMMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04976&json=true","fetch_graph":"https://pith.science/api/pith-number/XRPWNMMGDFMVSEPEPJBMFJGD5U/graph.json","fetch_events":"https://pith.science/api/pith-number/XRPWNMMGDFMVSEPEPJBMFJGD5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U/action/storage_attestation","attest_author":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U/action/author_attestation","sign_citation":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U/action/citation_signature","submit_replication":"https://pith.science/pith/XRPWNMMGDFMVSEPEPJBMFJGD5U/action/replication_record"}},"created_at":"2026-07-05T04:39:40.620305+00:00","updated_at":"2026-07-05T04:39:40.620305+00:00"}