{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NZ273PXTXPM7ERPDKFPBLKWGEX","short_pith_number":"pith:NZ273PXT","schema_version":"1.0","canonical_sha256":"6e75fdbef3bbd9f245e3515e15aac625d6f747fadf1a0c8dd94de716ba115a7e","source":{"kind":"arxiv","id":"2101.01169","version":5},"attestation_state":"computed","paper":{"title":"Transformers in Vision: A Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Munawar Hayat, Muzammal Naseer, Salman Khan, Syed Waqas Zamir","submitted_at":"2021-01-04T18:57:24Z","abstract_excerpt":"Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows process"},"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":"2101.01169","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-04T18:57:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cdbdb82368cb72f363a85718fff71c6d2dd248f34f5cbaa219c00811bd80122c","abstract_canon_sha256":"5cb11272f2b7a2884f4993400a97b0c917fcf5357f5d7c8d67dd94763be92bd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:38.461741Z","signature_b64":"CvS8pCmBNQBlHn8cKdp/f79CjSfjqlZXzL9Xu5hzOvnQRZqsV3gWKseKEdWgtUmtJPi9sorrVJG6F1sQ/hDOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e75fdbef3bbd9f245e3515e15aac625d6f747fadf1a0c8dd94de716ba115a7e","last_reissued_at":"2026-07-05T03:49:38.461344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:38.461344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers in Vision: A Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Munawar Hayat, Muzammal Naseer, Salman Khan, Syed Waqas Zamir","submitted_at":"2021-01-04T18:57:24Z","abstract_excerpt":"Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01169","kind":"arxiv","version":5},"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/2101.01169/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":"2101.01169","created_at":"2026-07-05T03:49:38.461404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01169v5","created_at":"2026-07-05T03:49:38.461404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01169","created_at":"2026-07-05T03:49:38.461404+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ273PXTXPM7","created_at":"2026-07-05T03:49:38.461404+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ273PXTXPM7ERPD","created_at":"2026-07-05T03:49:38.461404+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ273PXT","created_at":"2026-07-05T03:49:38.461404+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/NZ273PXTXPM7ERPDKFPBLKWGEX","json":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX.json","graph_json":"https://pith.science/api/pith-number/NZ273PXTXPM7ERPDKFPBLKWGEX/graph.json","events_json":"https://pith.science/api/pith-number/NZ273PXTXPM7ERPDKFPBLKWGEX/events.json","paper":"https://pith.science/paper/NZ273PXT"},"agent_actions":{"view_html":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX","download_json":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX.json","view_paper":"https://pith.science/paper/NZ273PXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01169&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ273PXTXPM7ERPDKFPBLKWGEX/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ273PXTXPM7ERPDKFPBLKWGEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX/action/storage_attestation","attest_author":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX/action/author_attestation","sign_citation":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX/action/citation_signature","submit_replication":"https://pith.science/pith/NZ273PXTXPM7ERPDKFPBLKWGEX/action/replication_record"}},"created_at":"2026-07-05T03:49:38.461404+00:00","updated_at":"2026-07-05T03:49:38.461404+00:00"}