{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UEHG5NQEA527WX663OO42ZVQ7C","short_pith_number":"pith:UEHG5NQE","canonical_record":{"source":{"id":"2006.03677","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T20:49:49Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"67d4996591b9247fd0545e089e1c524f8ec457a026d261bcaf3ee70ce7dc1417","abstract_canon_sha256":"dc0574356bff1f696801d591204d321277479d4014c45b4d97252b29be41a1e5"},"schema_version":"1.0"},"canonical_sha256":"a10e6eb6040775fb5fdedb9dcd66b0f8a7c9ff7ad2d28e9f1e9cf3fc1c2fa991","source":{"kind":"arxiv","id":"2006.03677","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03677","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03677v4","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03677","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"UEHG5NQEA527","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"UEHG5NQEA527WX66","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"UEHG5NQE","created_at":"2026-07-05T01:53:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UEHG5NQEA527WX663OO42ZVQ7C","target":"record","payload":{"canonical_record":{"source":{"id":"2006.03677","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T20:49:49Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"67d4996591b9247fd0545e089e1c524f8ec457a026d261bcaf3ee70ce7dc1417","abstract_canon_sha256":"dc0574356bff1f696801d591204d321277479d4014c45b4d97252b29be41a1e5"},"schema_version":"1.0"},"canonical_sha256":"a10e6eb6040775fb5fdedb9dcd66b0f8a7c9ff7ad2d28e9f1e9cf3fc1c2fa991","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:08.921739Z","signature_b64":"RZVmIlcHGDzJvqM3aNjZTki8gcVGW2TldDx6wlzxN+Oa71UTrB7oWafLBG6BsotyVojltiWJvUxZaqykYkMMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a10e6eb6040775fb5fdedb9dcd66b0f8a7c9ff7ad2d28e9f1e9cf3fc1c2fa991","last_reissued_at":"2026-07-05T01:53:08.921199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:08.921199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.03677","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irv0vh28SoT8YJGpacQyT5ID0SP0SScaj5jLKtacdsuQDmxeWkDKS6DsuhYqSdSefo/veX44FH6zqyZ4OcVSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:22.382005Z"},"content_sha256":"2c2513f3ec5ee1b2825a0813546b5803caf1d1875949a61ce7b530e50fd1112b","schema_version":"1.0","event_id":"sha256:2c2513f3ec5ee1b2825a0813546b5803caf1d1875949a61ce7b530e50fd1112b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UEHG5NQEA527WX663OO42ZVQ7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alvin Wan, Bichen Wu, Chenfeng Xu, Joseph Gonzalez, Kurt Keutzer, Masayoshi Tomizuka, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Zhicheng Yan","submitted_at":"2020-06-05T20:49:49Z","abstract_excerpt":"Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance; explicitly model all concepts across all images, regardless of content; and struggle to relate spatially-distant concepts. In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships. Critically, our Visual Transformer operates in a semantic token space, judiciousl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03677","kind":"arxiv","version":4},"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/2006.03677/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":"2026-07-05T01:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwhCqrKHoQaxN0CO+bmhhoqOFC3OUJ63Td3+86Z2pZ84OUXR6KMurDkAn0GRta5TsoWm5zx9Xen8r4cF4OT1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:22.382923Z"},"content_sha256":"f7d5dfd70d297d6e5a1cbccd8438775db2fbc72bf60fc5b835cc962b9d7dfdc6","schema_version":"1.0","event_id":"sha256:f7d5dfd70d297d6e5a1cbccd8438775db2fbc72bf60fc5b835cc962b9d7dfdc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UEHG5NQEA527WX663OO42ZVQ7C/bundle.json","state_url":"https://pith.science/pith/UEHG5NQEA527WX663OO42ZVQ7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UEHG5NQEA527WX663OO42ZVQ7C/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":"2026-08-17T23:02:22Z","links":{"resolver":"https://pith.science/pith/UEHG5NQEA527WX663OO42ZVQ7C","bundle":"https://pith.science/pith/UEHG5NQEA527WX663OO42ZVQ7C/bundle.json","state":"https://pith.science/pith/UEHG5NQEA527WX663OO42ZVQ7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UEHG5NQEA527WX663OO42ZVQ7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UEHG5NQEA527WX663OO42ZVQ7C","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":"dc0574356bff1f696801d591204d321277479d4014c45b4d97252b29be41a1e5","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T20:49:49Z","title_canon_sha256":"67d4996591b9247fd0545e089e1c524f8ec457a026d261bcaf3ee70ce7dc1417"},"schema_version":"1.0","source":{"id":"2006.03677","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03677","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03677v4","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03677","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"UEHG5NQEA527","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"UEHG5NQEA527WX66","created_at":"2026-07-05T01:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"UEHG5NQE","created_at":"2026-07-05T01:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:f7d5dfd70d297d6e5a1cbccd8438775db2fbc72bf60fc5b835cc962b9d7dfdc6","target":"graph","created_at":"2026-07-05T01:53:08Z","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/2006.03677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computer vision has achieved remarkable success by (a) representing images as uniformly-arranged pixel arrays and (b) convolving highly-localized features. However, convolutions treat all image pixels equally regardless of importance; explicitly model all concepts across all images, regardless of content; and struggle to relate spatially-distant concepts. In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships. Critically, our Visual Transformer operates in a semantic token space, judiciousl","authors_text":"Alvin Wan, Bichen Wu, Chenfeng Xu, Joseph Gonzalez, Kurt Keutzer, Masayoshi Tomizuka, Peizhao Zhang, Peter Vajda, Xiaoliang Dai, Zhicheng Yan","cross_cats":["cs.LG","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T20:49:49Z","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03677","kind":"arxiv","version":4},"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":"sha256:2c2513f3ec5ee1b2825a0813546b5803caf1d1875949a61ce7b530e50fd1112b","target":"record","created_at":"2026-07-05T01:53:08Z","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":"dc0574356bff1f696801d591204d321277479d4014c45b4d97252b29be41a1e5","cross_cats_sorted":["cs.LG","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-05T20:49:49Z","title_canon_sha256":"67d4996591b9247fd0545e089e1c524f8ec457a026d261bcaf3ee70ce7dc1417"},"schema_version":"1.0","source":{"id":"2006.03677","kind":"arxiv","version":4}},"canonical_sha256":"a10e6eb6040775fb5fdedb9dcd66b0f8a7c9ff7ad2d28e9f1e9cf3fc1c2fa991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a10e6eb6040775fb5fdedb9dcd66b0f8a7c9ff7ad2d28e9f1e9cf3fc1c2fa991","first_computed_at":"2026-07-05T01:53:08.921199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:08.921199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RZVmIlcHGDzJvqM3aNjZTki8gcVGW2TldDx6wlzxN+Oa71UTrB7oWafLBG6BsotyVojltiWJvUxZaqykYkMMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:08.921739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.03677","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c2513f3ec5ee1b2825a0813546b5803caf1d1875949a61ce7b530e50fd1112b","sha256:f7d5dfd70d297d6e5a1cbccd8438775db2fbc72bf60fc5b835cc962b9d7dfdc6"],"state_sha256":"b7c3a2524a1b056965de916a90f417c290e1a3b3028f561d309688fbc42c0e5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Cg870U+qpPvNa9qCcFtIcl+KwRdwL4TeH9zTZbHkHerViWnRgCoVJAHwrPlyLBaW7DnjCeIOvSe8ExE0xkiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:02:22.390422Z","bundle_sha256":"8459b1dc317dabddb4747ff959259803484d89f65407b7100da61376171f8806"}}