{"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"}