{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X35JJ7E3EXIQEV6WYYEITGLKFW","short_pith_number":"pith:X35JJ7E3","schema_version":"1.0","canonical_sha256":"befa94fc9b25d10257d6c60889996a2dad54c44a9e09557a405fa0894c4790bf","source":{"kind":"arxiv","id":"2308.15996","version":1},"attestation_state":"computed","paper":{"title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Masato Fujitake","submitted_at":"2023-08-30T12:37:03Z","abstract_excerpt":"Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features. In this study, we propose a simpler and more effective method for text recognition, known as the Decoder-only Transformer for Optical Character Recognition (DTrOCR). This method uses a decoder-only Transformer to take advantage of a generative language model that is pre-trained on a large corpus. We examined whether a generative language model that has been successful in natural language processing can also be"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.15996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T12:37:03Z","cross_cats_sorted":[],"title_canon_sha256":"7a3c7be7cfddee6960215e2edd64106ec085c002fe80017990224f238a553d5e","abstract_canon_sha256":"4f25b1fdad6f177e65a5af0a10061e0d28f0baf5cd6f8036cc08d312e8b0b096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:16.941355Z","signature_b64":"AUnBuoOimboTvFcACZrgJRkrc1SikZ9EVhGkrOXs2iUnOZwF55JVHC7od9JSfnb4riwa0Aw66w0K2iAKTMeFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"befa94fc9b25d10257d6c60889996a2dad54c44a9e09557a405fa0894c4790bf","last_reissued_at":"2026-07-05T06:46:16.940859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:16.940859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Masato Fujitake","submitted_at":"2023-08-30T12:37:03Z","abstract_excerpt":"Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features. In this study, we propose a simpler and more effective method for text recognition, known as the Decoder-only Transformer for Optical Character Recognition (DTrOCR). This method uses a decoder-only Transformer to take advantage of a generative language model that is pre-trained on a large corpus. We examined whether a generative language model that has been successful in natural language processing can also be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15996","kind":"arxiv","version":1},"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/2308.15996/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.15996","created_at":"2026-07-05T06:46:16.940918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15996v1","created_at":"2026-07-05T06:46:16.940918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15996","created_at":"2026-07-05T06:46:16.940918+00:00"},{"alias_kind":"pith_short_12","alias_value":"X35JJ7E3EXIQ","created_at":"2026-07-05T06:46:16.940918+00:00"},{"alias_kind":"pith_short_16","alias_value":"X35JJ7E3EXIQEV6W","created_at":"2026-07-05T06:46:16.940918+00:00"},{"alias_kind":"pith_short_8","alias_value":"X35JJ7E3","created_at":"2026-07-05T06:46:16.940918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20813","citing_title":"Adapting TrOCR for Printed Tigrinya Text Recognition: Word-Aware Loss Weighting for Cross-Script Transfer Learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW","json":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW.json","graph_json":"https://pith.science/api/pith-number/X35JJ7E3EXIQEV6WYYEITGLKFW/graph.json","events_json":"https://pith.science/api/pith-number/X35JJ7E3EXIQEV6WYYEITGLKFW/events.json","paper":"https://pith.science/paper/X35JJ7E3"},"agent_actions":{"view_html":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW","download_json":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW.json","view_paper":"https://pith.science/paper/X35JJ7E3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15996&json=true","fetch_graph":"https://pith.science/api/pith-number/X35JJ7E3EXIQEV6WYYEITGLKFW/graph.json","fetch_events":"https://pith.science/api/pith-number/X35JJ7E3EXIQEV6WYYEITGLKFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW/action/storage_attestation","attest_author":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW/action/author_attestation","sign_citation":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW/action/citation_signature","submit_replication":"https://pith.science/pith/X35JJ7E3EXIQEV6WYYEITGLKFW/action/replication_record"}},"created_at":"2026-07-05T06:46:16.940918+00:00","updated_at":"2026-07-05T06:46:16.940918+00:00"}