{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QXJI5MUPVQ4XNNRWFXBOVSE33D","short_pith_number":"pith:QXJI5MUP","canonical_record":{"source":{"id":"2109.10282","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T16:01:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"01b0666ea9d4bad14d14a476e9d9196fbb042fb6dcd8d6a7ebf2734123cf85ef","abstract_canon_sha256":"7e1b933274d74ed3d9d68d4b2a769e7f256c3525e87903bac4ba8a1dc52ac96a"},"schema_version":"1.0"},"canonical_sha256":"85d28eb28fac3976b6362dc2eac89bd8eeabfa9a77e16aec9c80c5adaf4e6e5f","source":{"kind":"arxiv","id":"2109.10282","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10282","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10282v5","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10282","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"QXJI5MUPVQ4X","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"QXJI5MUPVQ4XNNRW","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"QXJI5MUP","created_at":"2026-07-05T04:54:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QXJI5MUPVQ4XNNRWFXBOVSE33D","target":"record","payload":{"canonical_record":{"source":{"id":"2109.10282","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T16:01:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"01b0666ea9d4bad14d14a476e9d9196fbb042fb6dcd8d6a7ebf2734123cf85ef","abstract_canon_sha256":"7e1b933274d74ed3d9d68d4b2a769e7f256c3525e87903bac4ba8a1dc52ac96a"},"schema_version":"1.0"},"canonical_sha256":"85d28eb28fac3976b6362dc2eac89bd8eeabfa9a77e16aec9c80c5adaf4e6e5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:46.881403Z","signature_b64":"Q4ihAOEcKzBg3mWAzUAR6MKlf0qdYIbR1DzlNS3XEPL1keEyaD0nRt7I4ZNiREo470q2iTwNXyiczfbbT8yXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d28eb28fac3976b6362dc2eac89bd8eeabfa9a77e16aec9c80c5adaf4e6e5f","last_reissued_at":"2026-07-05T04:54:46.880982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:46.880982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.10282","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8VrMRNGY+/ZqQ2RsU3/6ihEW0hvbzY8DosVKRD2l5cxPAMUSH3WHDiQaOCB4w+I3sSZCz6UWCeXuHu2zn33AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:15:21.212875Z"},"content_sha256":"a00aa1b7f977ce79922cfd9fc6d4842251adc54d0c9d1f28d2e5164f32896720","schema_version":"1.0","event_id":"sha256:a00aa1b7f977ce79922cfd9fc6d4842251adc54d0c9d1f28d2e5164f32896720"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QXJI5MUPVQ4XNNRWFXBOVSE33D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Cha Zhang, Dinei Florencio, Furu Wei, Jingye Chen, Lei Cui, Minghao Li, Tengchao Lv, Yijuan Lu, Zhoujun Li","submitted_at":"2021-09-21T16:01:56Z","abstract_excerpt":"Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10282","kind":"arxiv","version":5},"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/2109.10282/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":"2026-07-05T04:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6ZKAbXSPH4H4iIQazBrYsdfDcHLYUl7ivPapdV0zn/Sdd2bH8SpKbL4Ptn6EzZ8dGywLvImPQQyCyBkXx+0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:15:21.213406Z"},"content_sha256":"3022081c12cb40fadb5bfefd42c07c55fe6097346eb84e9b141c1b6c41aeb822","schema_version":"1.0","event_id":"sha256:3022081c12cb40fadb5bfefd42c07c55fe6097346eb84e9b141c1b6c41aeb822"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/bundle.json","state_url":"https://pith.science/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/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":"2026-08-03T16:15:21Z","links":{"resolver":"https://pith.science/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D","bundle":"https://pith.science/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/bundle.json","state":"https://pith.science/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXJI5MUPVQ4XNNRWFXBOVSE33D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QXJI5MUPVQ4XNNRWFXBOVSE33D","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":"7e1b933274d74ed3d9d68d4b2a769e7f256c3525e87903bac4ba8a1dc52ac96a","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T16:01:56Z","title_canon_sha256":"01b0666ea9d4bad14d14a476e9d9196fbb042fb6dcd8d6a7ebf2734123cf85ef"},"schema_version":"1.0","source":{"id":"2109.10282","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10282","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10282v5","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10282","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"QXJI5MUPVQ4X","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"QXJI5MUPVQ4XNNRW","created_at":"2026-07-05T04:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"QXJI5MUP","created_at":"2026-07-05T04:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:3022081c12cb40fadb5bfefd42c07c55fe6097346eb84e9b141c1b6c41aeb822","target":"graph","created_at":"2026-07-05T04:54:46Z","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/2109.10282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effec","authors_text":"Cha Zhang, Dinei Florencio, Furu Wei, Jingye Chen, Lei Cui, Minghao Li, Tengchao Lv, Yijuan Lu, Zhoujun Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T16:01:56Z","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10282","kind":"arxiv","version":5},"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:a00aa1b7f977ce79922cfd9fc6d4842251adc54d0c9d1f28d2e5164f32896720","target":"record","created_at":"2026-07-05T04:54:46Z","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":"7e1b933274d74ed3d9d68d4b2a769e7f256c3525e87903bac4ba8a1dc52ac96a","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T16:01:56Z","title_canon_sha256":"01b0666ea9d4bad14d14a476e9d9196fbb042fb6dcd8d6a7ebf2734123cf85ef"},"schema_version":"1.0","source":{"id":"2109.10282","kind":"arxiv","version":5}},"canonical_sha256":"85d28eb28fac3976b6362dc2eac89bd8eeabfa9a77e16aec9c80c5adaf4e6e5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d28eb28fac3976b6362dc2eac89bd8eeabfa9a77e16aec9c80c5adaf4e6e5f","first_computed_at":"2026-07-05T04:54:46.880982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:46.880982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q4ihAOEcKzBg3mWAzUAR6MKlf0qdYIbR1DzlNS3XEPL1keEyaD0nRt7I4ZNiREo470q2iTwNXyiczfbbT8yXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:46.881403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10282","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00aa1b7f977ce79922cfd9fc6d4842251adc54d0c9d1f28d2e5164f32896720","sha256:3022081c12cb40fadb5bfefd42c07c55fe6097346eb84e9b141c1b6c41aeb822"],"state_sha256":"d20ecf05c17fe84bbb2cbc37ec01791d60a535ada3ce7cabf99953f9be9c7f55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"07qmiW2tQQtlqhR9lw2JN1Q/LlpTRk+CLTxIoF98a7zCpNJ98v5BVFNs6zKzA8XbTdLNbfByA/nHo1Tg5URyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:15:21.218881Z","bundle_sha256":"15b1eaa5ec56eff10bb145f11e6352495e652bcbeaa4564d0f43e186f38cadc2"}}