{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5WSNGUE6KH57NPIT62DYHVV4EL","short_pith_number":"pith:5WSNGUE6","schema_version":"1.0","canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","source":{"kind":"arxiv","id":"2305.17415","version":2},"attestation_state":"computed","paper":{"title":"Exploring Better Text Image Translation with Multimodal Codebook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Degen Huang, Jian Luan, Jiawei Yu, Jinsong Su, Wen Zhang, Xiang Li, Zhibin Lan","submitted_at":"2023-05-27T08:41:18Z","abstract_excerpt":"Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propos"},"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":"2305.17415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T08:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3a1be42491ae8c1c04aa2a07b37d6c1b7d8939097cb4a97d79d7d55fc97cd3b","abstract_canon_sha256":"d3b80e4bd32913b46fdefb9f1a154db74ea5169fda7d57db682d330aeb08991e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:50.830054Z","signature_b64":"+YP1WOPUnDn/yacQ6XaBCWdcajl6YgckanWj5qGYZ+jg2pKFPghi5UBGXvHt0BNke/lC0nzBgyZI0Rtu2VzVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda4d3509e51fbf6bd13f68783d6bc22f56ba370f8bcf18f54e36568a42d8012","last_reissued_at":"2026-07-05T06:16:50.829569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:50.829569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Better Text Image Translation with Multimodal Codebook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Degen Huang, Jian Luan, Jiawei Yu, Jinsong Su, Wen Zhang, Xiang Li, Zhibin Lan","submitted_at":"2023-05-27T08:41:18Z","abstract_excerpt":"Text image translation (TIT) aims to translate the source texts embedded in the image to target translations, which has a wide range of applications and thus has important research value. However, current studies on TIT are confronted with two main bottlenecks: 1) this task lacks a publicly available TIT dataset, 2) dominant models are constructed in a cascaded manner, which tends to suffer from the error propagation of optical character recognition (OCR). In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17415","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/2305.17415/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":"2305.17415","created_at":"2026-07-05T06:16:50.829627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17415v2","created_at":"2026-07-05T06:16:50.829627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17415","created_at":"2026-07-05T06:16:50.829627+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WSNGUE6KH57","created_at":"2026-07-05T06:16:50.829627+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WSNGUE6KH57NPIT","created_at":"2026-07-05T06:16:50.829627+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WSNGUE6","created_at":"2026-07-05T06:16:50.829627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24333","citing_title":"UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24675","citing_title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16943","citing_title":"MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL","json":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL.json","graph_json":"https://pith.science/api/pith-number/5WSNGUE6KH57NPIT62DYHVV4EL/graph.json","events_json":"https://pith.science/api/pith-number/5WSNGUE6KH57NPIT62DYHVV4EL/events.json","paper":"https://pith.science/paper/5WSNGUE6"},"agent_actions":{"view_html":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL","download_json":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL.json","view_paper":"https://pith.science/paper/5WSNGUE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17415&json=true","fetch_graph":"https://pith.science/api/pith-number/5WSNGUE6KH57NPIT62DYHVV4EL/graph.json","fetch_events":"https://pith.science/api/pith-number/5WSNGUE6KH57NPIT62DYHVV4EL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/action/storage_attestation","attest_author":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/action/author_attestation","sign_citation":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/action/citation_signature","submit_replication":"https://pith.science/pith/5WSNGUE6KH57NPIT62DYHVV4EL/action/replication_record"}},"created_at":"2026-07-05T06:16:50.829627+00:00","updated_at":"2026-07-05T06:16:50.829627+00:00"}