{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V2I57UBTYID6B5PNSP5VTOBVHR","short_pith_number":"pith:V2I57UBT","canonical_record":{"source":{"id":"2205.11239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T14:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"159c67b348c30b6278a177251015e5d8a1395449931164d2aa1a19d97483d039","abstract_canon_sha256":"143ace6a21d285e3100de7947fc7c12bd972bd5950025a6c7ec06b0d9358c5e4"},"schema_version":"1.0"},"canonical_sha256":"ae91dfd033c207e0f5ed93fb59b8353c5f253ec1dacc6868ef312a59e8d7f9ec","source":{"kind":"arxiv","id":"2205.11239","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11239","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11239v2","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11239","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"V2I57UBTYID6","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"V2I57UBTYID6B5PN","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"V2I57UBT","created_at":"2026-07-05T04:26:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V2I57UBTYID6B5PNSP5VTOBVHR","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T14:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"159c67b348c30b6278a177251015e5d8a1395449931164d2aa1a19d97483d039","abstract_canon_sha256":"143ace6a21d285e3100de7947fc7c12bd972bd5950025a6c7ec06b0d9358c5e4"},"schema_version":"1.0"},"canonical_sha256":"ae91dfd033c207e0f5ed93fb59b8353c5f253ec1dacc6868ef312a59e8d7f9ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:04.921455Z","signature_b64":"0vTIa4G2W0vp7k68ySd/zZcZgZndJeKtcZkMDrPAzhGcLnBXxk/Ox/06PshgVlVhtisxTosbnsK2JOws6PqdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae91dfd033c207e0f5ed93fb59b8353c5f253ec1dacc6868ef312a59e8d7f9ec","last_reissued_at":"2026-07-05T04:26:04.920996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:04.920996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11239","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lc1dM0CTmIsVWAOQkLqaFXJtCd54htcmgeMs8MAUGkRNiNOC53JGTcm2Fnua82o4DHbxmo8IxkfRebGbWbVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:33:00.815295Z"},"content_sha256":"29bd314fde95332af87828ed8ec56b1c2efad6346bfe9970b89199a1304607e0","schema_version":"1.0","event_id":"sha256:29bd314fde95332af87828ed8ec56b1c2efad6346bfe9970b89199a1304607e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V2I57UBTYID6B5PNSP5VTOBVHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision Transformer: Vit and its Derivatives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Zujun Fu","submitted_at":"2022-05-12T14:02:39Z","abstract_excerpt":"Transformer, an attention-based encoder-decoder architecture, has not only revolutionized the field of natural language processing (NLP), but has also done some pioneering work in the field of computer vision (CV). Compared to convolutional neural networks (CNNs), the Vision Transformer (ViT) relies on excellent modeling capabilities to achieve very good performance on several benchmarks such as ImageNet, COCO, and ADE20k. ViT is inspired by the self-attention mechanism in natural language processing, where word embeddings are replaced with patch embeddings.\n  This paper reviews the derivative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11239","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/2205.11239/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X5VU0nPhIlUjX545rd+htABoDfjL8M5rhTK/uwmHD9IbvZoES1YBEMgB0SNOHwbXyv79+gIzTxr5qAw1+87tDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:33:00.815777Z"},"content_sha256":"1eb1f50c65e05190213ce9d172cbac76476958b807b5899b2b12d3f214969fac","schema_version":"1.0","event_id":"sha256:1eb1f50c65e05190213ce9d172cbac76476958b807b5899b2b12d3f214969fac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2I57UBTYID6B5PNSP5VTOBVHR/bundle.json","state_url":"https://pith.science/pith/V2I57UBTYID6B5PNSP5VTOBVHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2I57UBTYID6B5PNSP5VTOBVHR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T03:33:00Z","links":{"resolver":"https://pith.science/pith/V2I57UBTYID6B5PNSP5VTOBVHR","bundle":"https://pith.science/pith/V2I57UBTYID6B5PNSP5VTOBVHR/bundle.json","state":"https://pith.science/pith/V2I57UBTYID6B5PNSP5VTOBVHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2I57UBTYID6B5PNSP5VTOBVHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V2I57UBTYID6B5PNSP5VTOBVHR","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":"143ace6a21d285e3100de7947fc7c12bd972bd5950025a6c7ec06b0d9358c5e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T14:02:39Z","title_canon_sha256":"159c67b348c30b6278a177251015e5d8a1395449931164d2aa1a19d97483d039"},"schema_version":"1.0","source":{"id":"2205.11239","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11239","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11239v2","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11239","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"V2I57UBTYID6","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"V2I57UBTYID6B5PN","created_at":"2026-07-05T04:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"V2I57UBT","created_at":"2026-07-05T04:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:1eb1f50c65e05190213ce9d172cbac76476958b807b5899b2b12d3f214969fac","target":"graph","created_at":"2026-07-05T04:26:04Z","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/2205.11239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer, an attention-based encoder-decoder architecture, has not only revolutionized the field of natural language processing (NLP), but has also done some pioneering work in the field of computer vision (CV). Compared to convolutional neural networks (CNNs), the Vision Transformer (ViT) relies on excellent modeling capabilities to achieve very good performance on several benchmarks such as ImageNet, COCO, and ADE20k. ViT is inspired by the self-attention mechanism in natural language processing, where word embeddings are replaced with patch embeddings.\n  This paper reviews the derivative","authors_text":"Zujun Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T14:02:39Z","title":"Vision Transformer: Vit and its Derivatives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11239","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":"sha256:29bd314fde95332af87828ed8ec56b1c2efad6346bfe9970b89199a1304607e0","target":"record","created_at":"2026-07-05T04:26:04Z","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":"143ace6a21d285e3100de7947fc7c12bd972bd5950025a6c7ec06b0d9358c5e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T14:02:39Z","title_canon_sha256":"159c67b348c30b6278a177251015e5d8a1395449931164d2aa1a19d97483d039"},"schema_version":"1.0","source":{"id":"2205.11239","kind":"arxiv","version":2}},"canonical_sha256":"ae91dfd033c207e0f5ed93fb59b8353c5f253ec1dacc6868ef312a59e8d7f9ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae91dfd033c207e0f5ed93fb59b8353c5f253ec1dacc6868ef312a59e8d7f9ec","first_computed_at":"2026-07-05T04:26:04.920996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:04.920996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0vTIa4G2W0vp7k68ySd/zZcZgZndJeKtcZkMDrPAzhGcLnBXxk/Ox/06PshgVlVhtisxTosbnsK2JOws6PqdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:04.921455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11239","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29bd314fde95332af87828ed8ec56b1c2efad6346bfe9970b89199a1304607e0","sha256:1eb1f50c65e05190213ce9d172cbac76476958b807b5899b2b12d3f214969fac"],"state_sha256":"3cf67f1966b1f93cc24657699e57413bd6c5fe8b503e3abd25b2cb131cb3e763"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2apZjjFxZxnNeljH9E5zwD/7sbfqCauO/JkjALV/oiUcsE5eafP+Y9tLpRp/9cpcf4cq+xcJI2n3IIqQZgM5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:33:00.819047Z","bundle_sha256":"cb1b8f14eb8c5e7eca62167b5e9d078d3db95cdd996a78e60ef027545a0bbaae"}}