{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:U5G67EGIYSYW5253IWMGPHQXMB","short_pith_number":"pith:U5G67EGI","canonical_record":{"source":{"id":"2111.10493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-20T01:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"4eb266f70b9d870d0e13689fda46ca1c9d4136727ceed6c84e3830185d06f653","abstract_canon_sha256":"3fd4c598334ccfda2c59e968f3856d6233032d6a271254d62effb82571ccd31d"},"schema_version":"1.0"},"canonical_sha256":"a74def90c8c4b16eebbb4598679e1760546fa53071ea3fdcc31fe50692def53f","source":{"kind":"arxiv","id":"2111.10493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10493","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10493v2","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10493","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"U5G67EGIYSYW","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"U5G67EGIYSYW5253","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"U5G67EGI","created_at":"2026-07-05T04:10:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:U5G67EGIYSYW5253IWMGPHQXMB","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-20T01:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"4eb266f70b9d870d0e13689fda46ca1c9d4136727ceed6c84e3830185d06f653","abstract_canon_sha256":"3fd4c598334ccfda2c59e968f3856d6233032d6a271254d62effb82571ccd31d"},"schema_version":"1.0"},"canonical_sha256":"a74def90c8c4b16eebbb4598679e1760546fa53071ea3fdcc31fe50692def53f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:51.872267Z","signature_b64":"GWJXl98LSAr9mqZyWFjAE55QMPaGNB0g/tOsEEZfzYFVlIjvMq0Ad0nwZgPdYi7sK6QjgPzUfUBdgyqfEPptCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a74def90c8c4b16eebbb4598679e1760546fa53071ea3fdcc31fe50692def53f","last_reissued_at":"2026-07-05T04:10:51.871792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:51.871792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10493","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":"2026-07-05T04:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Naf01SVMAtQiFKWVirNSDRX00IPaMrxdFXlqanOyaMmEaz+zypSvg4SQCcspCZLm1WLj5TOuRBcKXAPcuCuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:08:31.652899Z"},"content_sha256":"ebb5c104e87ade4a9b49d91835d4140a5d338906606aac19e70cbbc9c26670e8","schema_version":"1.0","event_id":"sha256:ebb5c104e87ade4a9b49d91835d4140a5d338906606aac19e70cbbc9c26670e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:U5G67EGIYSYW5253IWMGPHQXMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Representations Strengthen Vision Transformer Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Chengzhi Mao, Irfan Essa, Lu Jiang, Mostafa Dehghani, Rahul Sukthankar","submitted_at":"2021-11-20T01:49:56Z","abstract_excerpt":"Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on ImageNet are overly reliant on local textures and fail to make adequate use of shape information. ViTs thus have difficulties generalizing to out-of-distribution, real-world data. To address this deficiency, we present a simple and effective architecture modification to ViT's input layer by adding discrete tokens produced by a vector-quantized encoder. Different fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10493","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/2111.10493/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":"2026-07-05T04:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y1NmgmFPTAG4tOxmmOwbMzKy/oYy02blwAm8/fJU5OUmY0VelBjDOZyT2JIySqNK/98V/cZI6iTUqb0gj/ZIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:08:31.653423Z"},"content_sha256":"8d93acf2b1a47fcf708dd30fa1724f41c6c2a3a8f54522ed9ffa86b835da4de6","schema_version":"1.0","event_id":"sha256:8d93acf2b1a47fcf708dd30fa1724f41c6c2a3a8f54522ed9ffa86b835da4de6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5G67EGIYSYW5253IWMGPHQXMB/bundle.json","state_url":"https://pith.science/pith/U5G67EGIYSYW5253IWMGPHQXMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5G67EGIYSYW5253IWMGPHQXMB/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":"2026-08-06T15:08:31Z","links":{"resolver":"https://pith.science/pith/U5G67EGIYSYW5253IWMGPHQXMB","bundle":"https://pith.science/pith/U5G67EGIYSYW5253IWMGPHQXMB/bundle.json","state":"https://pith.science/pith/U5G67EGIYSYW5253IWMGPHQXMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5G67EGIYSYW5253IWMGPHQXMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U5G67EGIYSYW5253IWMGPHQXMB","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":"3fd4c598334ccfda2c59e968f3856d6233032d6a271254d62effb82571ccd31d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-20T01:49:56Z","title_canon_sha256":"4eb266f70b9d870d0e13689fda46ca1c9d4136727ceed6c84e3830185d06f653"},"schema_version":"1.0","source":{"id":"2111.10493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10493","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10493v2","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10493","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"U5G67EGIYSYW","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"U5G67EGIYSYW5253","created_at":"2026-07-05T04:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"U5G67EGI","created_at":"2026-07-05T04:10:51Z"}],"graph_snapshots":[{"event_id":"sha256:8d93acf2b1a47fcf708dd30fa1724f41c6c2a3a8f54522ed9ffa86b835da4de6","target":"graph","created_at":"2026-07-05T04:10:51Z","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/2111.10493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on ImageNet are overly reliant on local textures and fail to make adequate use of shape information. ViTs thus have difficulties generalizing to out-of-distribution, real-world data. To address this deficiency, we present a simple and effective architecture modification to ViT's input layer by adding discrete tokens produced by a vector-quantized encoder. Different fr","authors_text":"Carl Vondrick, Chengzhi Mao, Irfan Essa, Lu Jiang, Mostafa Dehghani, Rahul Sukthankar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-20T01:49:56Z","title":"Discrete Representations Strengthen Vision Transformer Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10493","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:ebb5c104e87ade4a9b49d91835d4140a5d338906606aac19e70cbbc9c26670e8","target":"record","created_at":"2026-07-05T04:10:51Z","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":"3fd4c598334ccfda2c59e968f3856d6233032d6a271254d62effb82571ccd31d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-20T01:49:56Z","title_canon_sha256":"4eb266f70b9d870d0e13689fda46ca1c9d4136727ceed6c84e3830185d06f653"},"schema_version":"1.0","source":{"id":"2111.10493","kind":"arxiv","version":2}},"canonical_sha256":"a74def90c8c4b16eebbb4598679e1760546fa53071ea3fdcc31fe50692def53f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a74def90c8c4b16eebbb4598679e1760546fa53071ea3fdcc31fe50692def53f","first_computed_at":"2026-07-05T04:10:51.871792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:51.871792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GWJXl98LSAr9mqZyWFjAE55QMPaGNB0g/tOsEEZfzYFVlIjvMq0Ad0nwZgPdYi7sK6QjgPzUfUBdgyqfEPptCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:51.872267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebb5c104e87ade4a9b49d91835d4140a5d338906606aac19e70cbbc9c26670e8","sha256:8d93acf2b1a47fcf708dd30fa1724f41c6c2a3a8f54522ed9ffa86b835da4de6"],"state_sha256":"37872ac8e71aa1f35c023aeb421047120891ebd75bd3eb633df4ba3c417f2c84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lY5MfZKBhSr0mDRfr3VJMoiIbz0YPSqM+3zNb5EFcXe7/BeMxhrGDe0OXIWsvMayqhpJeZfrwxXbyqghxA/ZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:08:31.656929Z","bundle_sha256":"19c90971ec04adb1b56005eb3e00a932d9dcbad1fe561ab21730fa1beab187c4"}}