{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H4Q3CRZLLJGO52LL37KJPDSRIY","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":"4788e8a9563b4755378c2a640da3cd365f790b7fd13d85a1c31701544975e213","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-02T03:30:17Z","title_canon_sha256":"fb32c26f190d505814f8140d6153c2a5407e1af3de799ec0211c1e3872dded70"},"schema_version":"1.0","source":{"id":"2111.01353","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01353","created_at":"2026-07-05T03:28:42Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01353v2","created_at":"2026-07-05T03:28:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01353","created_at":"2026-07-05T03:28:42Z"},{"alias_kind":"pith_short_12","alias_value":"H4Q3CRZLLJGO","created_at":"2026-07-05T03:28:42Z"},{"alias_kind":"pith_short_16","alias_value":"H4Q3CRZLLJGO52LL","created_at":"2026-07-05T03:28:42Z"},{"alias_kind":"pith_short_8","alias_value":"H4Q3CRZL","created_at":"2026-07-05T03:28:42Z"}],"graph_snapshots":[{"event_id":"sha256:8f6f055b50011bc7f4087385557f73c947f55884b9cfffdd4ac90e106301b302","target":"graph","created_at":"2026-07-05T03:28:42Z","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/2111.01353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vision tasks without using convolutional layers. This naturally leads to the following questions: Can a self-attention layer of ViT express any convolution operation? In this work, we prove that a single ViT layer with image patches as the input can perform any convolution operation constructively, where the multi-head attention mechanism and the relative positional encoding play essential roles. We further provide a l","authors_text":"Cho-Jui Hsieh, Di He, Shanda Li, Xiangning Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-02T03:30:17Z","title":"Can Vision Transformers Perform Convolution?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01353","kind":"arxiv","version":2},"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":"sha256:4de720abd47f19b0fea523c0cea63aa9b3a581a30518cca9677f1171901366ee","target":"record","created_at":"2026-07-05T03:28:42Z","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":"4788e8a9563b4755378c2a640da3cd365f790b7fd13d85a1c31701544975e213","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-02T03:30:17Z","title_canon_sha256":"fb32c26f190d505814f8140d6153c2a5407e1af3de799ec0211c1e3872dded70"},"schema_version":"1.0","source":{"id":"2111.01353","kind":"arxiv","version":2}},"canonical_sha256":"3f21b1472b5a4ceee96bdfd4978e51462a4c416031cad6b529d810b4f48afbcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f21b1472b5a4ceee96bdfd4978e51462a4c416031cad6b529d810b4f48afbcf","first_computed_at":"2026-07-05T03:28:42.494674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:28:42.494674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjSe8sx1OCqymQdiYX7NvCrpPTQ0ups5ihBzIHiB8KOcIHQEperFRoSwB4Pu60rLyX7ldsh+3DpcRj/OIjqjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:28:42.495017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.01353","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4de720abd47f19b0fea523c0cea63aa9b3a581a30518cca9677f1171901366ee","sha256:8f6f055b50011bc7f4087385557f73c947f55884b9cfffdd4ac90e106301b302"],"state_sha256":"ee072b3c52830825516f9f3137dee968375debd8430bac367644b3601e2facb0"}