{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H5WYHR4LAYEXRNPCSFHVEKKSBW","short_pith_number":"pith:H5WYHR4L","schema_version":"1.0","canonical_sha256":"3f6d83c78b060978b5e2914f5229520d8b2710e7d915b32776a8a62ad7f80d63","source":{"kind":"arxiv","id":"2310.16809","version":2},"attestation_state":"computed","paper":{"title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dezhi Peng, Lianwen Jin, Wenhui Liao, Xinhong Chen, Yongxin Shi, Yuyi Zhang, Zening Lin","submitted_at":"2023-10-25T17:38:55Z","abstract_excerpt":"This paper presents a comprehensive evaluation of the Optical Character Recognition (OCR) capabilities of the recently released GPT-4V(ision), a Large Multimodal Model (LMM). We assess the model's performance across a range of OCR tasks, including scene text recognition, handwritten text recognition, handwritten mathematical expression recognition, table structure recognition, and information extraction from visually-rich document. The evaluation reveals that GPT-4V performs well in recognizing and understanding Latin contents, but struggles with multilingual scenarios and complex tasks. Speci"},"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":"2310.16809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T17:38:55Z","cross_cats_sorted":[],"title_canon_sha256":"99e198ce7c3fe086bd94b6fd3f74778ea26539ebee44bc03aaed7920ebaecc19","abstract_canon_sha256":"c76710685ddaa1d22aa5de47948fb067b7a5036da1f81a38503b7d39598b824e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:37.580122Z","signature_b64":"Mq8gIrtoxNw369ML9ruwZz004/c196Zz8yYNoAvJPeMTs9NILBE9vTkJoAv55jEoUs4Ogd80vtsACM2rSk5BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f6d83c78b060978b5e2914f5229520d8b2710e7d915b32776a8a62ad7f80d63","last_reissued_at":"2026-07-05T07:06:37.579079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:37.579079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dezhi Peng, Lianwen Jin, Wenhui Liao, Xinhong Chen, Yongxin Shi, Yuyi Zhang, Zening Lin","submitted_at":"2023-10-25T17:38:55Z","abstract_excerpt":"This paper presents a comprehensive evaluation of the Optical Character Recognition (OCR) capabilities of the recently released GPT-4V(ision), a Large Multimodal Model (LMM). We assess the model's performance across a range of OCR tasks, including scene text recognition, handwritten text recognition, handwritten mathematical expression recognition, table structure recognition, and information extraction from visually-rich document. The evaluation reveals that GPT-4V performs well in recognizing and understanding Latin contents, but struggles with multilingual scenarios and complex tasks. Speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16809","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/2310.16809/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":"2310.16809","created_at":"2026-07-05T07:06:37.579136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16809v2","created_at":"2026-07-05T07:06:37.579136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16809","created_at":"2026-07-05T07:06:37.579136+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5WYHR4LAYEX","created_at":"2026-07-05T07:06:37.579136+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5WYHR4LAYEXRNPC","created_at":"2026-07-05T07:06:37.579136+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5WYHR4L","created_at":"2026-07-05T07:06:37.579136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16504","citing_title":"From Handwriting to Structured Data: Benchmarking AI Digitisation of Handwritten Forms","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW","json":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW.json","graph_json":"https://pith.science/api/pith-number/H5WYHR4LAYEXRNPCSFHVEKKSBW/graph.json","events_json":"https://pith.science/api/pith-number/H5WYHR4LAYEXRNPCSFHVEKKSBW/events.json","paper":"https://pith.science/paper/H5WYHR4L"},"agent_actions":{"view_html":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW","download_json":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW.json","view_paper":"https://pith.science/paper/H5WYHR4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16809&json=true","fetch_graph":"https://pith.science/api/pith-number/H5WYHR4LAYEXRNPCSFHVEKKSBW/graph.json","fetch_events":"https://pith.science/api/pith-number/H5WYHR4LAYEXRNPCSFHVEKKSBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW/action/storage_attestation","attest_author":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW/action/author_attestation","sign_citation":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW/action/citation_signature","submit_replication":"https://pith.science/pith/H5WYHR4LAYEXRNPCSFHVEKKSBW/action/replication_record"}},"created_at":"2026-07-05T07:06:37.579136+00:00","updated_at":"2026-07-05T07:06:37.579136+00:00"}