{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5W4EX2JB7DIUOWJXEVK4COMBZ5","short_pith_number":"pith:5W4EX2JB","schema_version":"1.0","canonical_sha256":"edb84be921f8d14759372555c13981cf47823194a706534665a9ed20e8a1bf86","source":{"kind":"arxiv","id":"2305.05166","version":2},"attestation_state":"computed","paper":{"title":"E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Cong Ma, Mei Tu, Yang Zhao, Yaping Zhang, Yu Zhou","submitted_at":"2023-05-09T04:25:52Z","abstract_excerpt":"Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datase"},"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":"2305.05166","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T04:25:52Z","cross_cats_sorted":[],"title_canon_sha256":"063d2674953b877c1a50f42b490b5d417475f98089423d5ff66efec087a575b9","abstract_canon_sha256":"5596600c03bf2fab13a84f3e739304ce4f9e43441ce3524bcefa13b81118dcda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:55.991811Z","signature_b64":"zwYhJ/bhviVPEpCBJANpB9tAIpt4cFPuySPzNMpjCy9gkZasvTQK29Z7r2xvLwA0n45hZVEpNqYw7tD5E4ivCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb84be921f8d14759372555c13981cf47823194a706534665a9ed20e8a1bf86","last_reissued_at":"2026-07-05T06:08:55.991394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:55.991394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Cong Ma, Mei Tu, Yang Zhao, Yaping Zhang, Yu Zhou","submitted_at":"2023-05-09T04:25:52Z","abstract_excerpt":"Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05166","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/2305.05166/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":"2305.05166","created_at":"2026-07-05T06:08:55.991451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05166v2","created_at":"2026-07-05T06:08:55.991451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05166","created_at":"2026-07-05T06:08:55.991451+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W4EX2JB7DIU","created_at":"2026-07-05T06:08:55.991451+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W4EX2JB7DIUOWJX","created_at":"2026-07-05T06:08:55.991451+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W4EX2JB","created_at":"2026-07-05T06:08:55.991451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5","json":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5.json","graph_json":"https://pith.science/api/pith-number/5W4EX2JB7DIUOWJXEVK4COMBZ5/graph.json","events_json":"https://pith.science/api/pith-number/5W4EX2JB7DIUOWJXEVK4COMBZ5/events.json","paper":"https://pith.science/paper/5W4EX2JB"},"agent_actions":{"view_html":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5","download_json":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5.json","view_paper":"https://pith.science/paper/5W4EX2JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05166&json=true","fetch_graph":"https://pith.science/api/pith-number/5W4EX2JB7DIUOWJXEVK4COMBZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/5W4EX2JB7DIUOWJXEVK4COMBZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5/action/storage_attestation","attest_author":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5/action/author_attestation","sign_citation":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5/action/citation_signature","submit_replication":"https://pith.science/pith/5W4EX2JB7DIUOWJXEVK4COMBZ5/action/replication_record"}},"created_at":"2026-07-05T06:08:55.991451+00:00","updated_at":"2026-07-05T06:08:55.991451+00:00"}