{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:C4XVLYL3OBIMQ4PXMN7M5GNPQJ","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":"76bd273394510aa404197984fd88bd22ed4f84556f6d36f1b7fd6ed01f036c48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T17:58:22Z","title_canon_sha256":"8099e65048a3d7088665dc479e8400a8773a872190dbd46a21ee0ea864ac8e2e"},"schema_version":"1.0","source":{"id":"2103.15808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15808","created_at":"2026-07-05T02:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15808v1","created_at":"2026-07-05T02:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15808","created_at":"2026-07-05T02:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"C4XVLYL3OBIM","created_at":"2026-07-05T02:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"C4XVLYL3OBIMQ4PX","created_at":"2026-07-05T02:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"C4XVLYL3","created_at":"2026-07-05T02:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:e2a08e53bb7df1165730e0beb9f0bd88574e70fb6628e8f9e6f8f2cb937595ec","target":"graph","created_at":"2026-07-05T02:27:10Z","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/2103.15808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is accomplished through two primary modifications: a hierarchy of Transformers containing a new convolutional token embedding, and a convolutional Transformer block leveraging a convolutional projection. These changes introduce desirable properties of convolutional neural networks (CNNs) to the ViT architecture (\\ie shift, scale, and distortion invariance) whil","authors_text":"Bin Xiao, Haiping Wu, Lei Zhang, Lu Yuan, Mengchen Liu, Noel Codella, Xiyang Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T17:58:22Z","title":"CvT: Introducing Convolutions to Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15808","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":"sha256:57ac922b83cd7403a9d5369eb3092e2d69dda37566759ac136989bc88e795bb6","target":"record","created_at":"2026-07-05T02:27:10Z","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":"76bd273394510aa404197984fd88bd22ed4f84556f6d36f1b7fd6ed01f036c48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T17:58:22Z","title_canon_sha256":"8099e65048a3d7088665dc479e8400a8773a872190dbd46a21ee0ea864ac8e2e"},"schema_version":"1.0","source":{"id":"2103.15808","kind":"arxiv","version":1}},"canonical_sha256":"172f55e17b7050c871f7637ece99af827cc087ac2a482d361284f1652c6e54ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"172f55e17b7050c871f7637ece99af827cc087ac2a482d361284f1652c6e54ba","first_computed_at":"2026-07-05T02:27:10.026109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:27:10.026109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XVTM+5KLz+P3ih4g0+lj58PHK5LyO9zgFYO9FGVOdUL8Ke/hJ2Q0ZK8kVS6KLxK5jIO7c/0gP1xM6Sa7iJr1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:27:10.026611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.15808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57ac922b83cd7403a9d5369eb3092e2d69dda37566759ac136989bc88e795bb6","sha256:e2a08e53bb7df1165730e0beb9f0bd88574e70fb6628e8f9e6f8f2cb937595ec"],"state_sha256":"bb53d8c6dd19d916a122e4ba96e45e0111647f2ac2e0f9bf8550d7b5158b4485"}