{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCVAPGCBQ5YN4HIMVW5D2WWX6W","short_pith_number":"pith:OCVAPGCB","schema_version":"1.0","canonical_sha256":"70aa0798418770de1d0cadba3d5ad7f587c341c7946335a7aaf450add6e2c422","source":{"kind":"arxiv","id":"2504.17315","version":1},"attestation_state":"computed","paper":{"title":"DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chong Li, Hao Yang, Junhao Zhu, Ning Xie, Pengfei Li, Shuang Wu, Tengfei Song, Weidong Zhang, Zhanglin Wu","submitted_at":"2025-04-24T07:17:59Z","abstract_excerpt":"This paper presents the technical solution proposed by Huawei Translation Service Center (HW-TSC) for the \"End-to-End Document Image Machine Translation for Complex Layouts\" competition at the 19th International Conference on Document Analysis and Recognition (DIMT25@ICDAR2025). Leveraging state-of-the-art open-source large vision-language model (LVLM), we introduce a training framework that combines multi-task learning with perceptual chain-of-thought to develop a comprehensive end-to-end document translation system. During the inference phase, we apply minimum Bayesian decoding and post-proc"},"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":"2504.17315","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T07:17:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"586b0a13f8b39242fec54dd232cf9532be5eb8fea21f817071daf699eb2dd4b1","abstract_canon_sha256":"a65b2ccfef39d42f33b0866aa5e12793e7938e613ef7244c7326bbd47725a706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:26.525584Z","signature_b64":"q9iap0Ixggwq7VilsanVUb96TOochtyIUs/eo0ZP2UYgbOdt8lx9zql1L0hJxUM3ga8m8m2sgZt+elsmEf34Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70aa0798418770de1d0cadba3d5ad7f587c341c7946335a7aaf450add6e2c422","last_reissued_at":"2026-07-05T10:53:26.525095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:26.525095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chong Li, Hao Yang, Junhao Zhu, Ning Xie, Pengfei Li, Shuang Wu, Tengfei Song, Weidong Zhang, Zhanglin Wu","submitted_at":"2025-04-24T07:17:59Z","abstract_excerpt":"This paper presents the technical solution proposed by Huawei Translation Service Center (HW-TSC) for the \"End-to-End Document Image Machine Translation for Complex Layouts\" competition at the 19th International Conference on Document Analysis and Recognition (DIMT25@ICDAR2025). Leveraging state-of-the-art open-source large vision-language model (LVLM), we introduce a training framework that combines multi-task learning with perceptual chain-of-thought to develop a comprehensive end-to-end document translation system. During the inference phase, we apply minimum Bayesian decoding and post-proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17315","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/2504.17315/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":"2504.17315","created_at":"2026-07-05T10:53:26.525181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17315v1","created_at":"2026-07-05T10:53:26.525181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17315","created_at":"2026-07-05T10:53:26.525181+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCVAPGCBQ5YN","created_at":"2026-07-05T10:53:26.525181+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCVAPGCBQ5YN4HIM","created_at":"2026-07-05T10:53:26.525181+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCVAPGCB","created_at":"2026-07-05T10:53:26.525181+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/OCVAPGCBQ5YN4HIMVW5D2WWX6W","json":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W.json","graph_json":"https://pith.science/api/pith-number/OCVAPGCBQ5YN4HIMVW5D2WWX6W/graph.json","events_json":"https://pith.science/api/pith-number/OCVAPGCBQ5YN4HIMVW5D2WWX6W/events.json","paper":"https://pith.science/paper/OCVAPGCB"},"agent_actions":{"view_html":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W","download_json":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W.json","view_paper":"https://pith.science/paper/OCVAPGCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17315&json=true","fetch_graph":"https://pith.science/api/pith-number/OCVAPGCBQ5YN4HIMVW5D2WWX6W/graph.json","fetch_events":"https://pith.science/api/pith-number/OCVAPGCBQ5YN4HIMVW5D2WWX6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W/action/storage_attestation","attest_author":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W/action/author_attestation","sign_citation":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W/action/citation_signature","submit_replication":"https://pith.science/pith/OCVAPGCBQ5YN4HIMVW5D2WWX6W/action/replication_record"}},"created_at":"2026-07-05T10:53:26.525181+00:00","updated_at":"2026-07-05T10:53:26.525181+00:00"}