{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OCVAPGCBQ5YN4HIMVW5D2WWX6W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a65b2ccfef39d42f33b0866aa5e12793e7938e613ef7244c7326bbd47725a706","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T07:17:59Z","title_canon_sha256":"586b0a13f8b39242fec54dd232cf9532be5eb8fea21f817071daf699eb2dd4b1"},"schema_version":"1.0","source":{"id":"2504.17315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17315","created_at":"2026-07-05T10:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17315v1","created_at":"2026-07-05T10:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17315","created_at":"2026-07-05T10:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"OCVAPGCBQ5YN","created_at":"2026-07-05T10:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"OCVAPGCBQ5YN4HIM","created_at":"2026-07-05T10:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"OCVAPGCB","created_at":"2026-07-05T10:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:c5d03b4ad9a5c228ca90c1eb3d5013ce449fa6bde2e8dc66f81029017e746abd","target":"graph","created_at":"2026-07-05T10:53:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.17315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chong Li, Hao Yang, Junhao Zhu, Ning Xie, Pengfei Li, Shuang Wu, Tengfei Song, Weidong Zhang, Zhanglin Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T07:17:59Z","title":"DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17315","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88592c7caa65e78803426492a7e37163884c31b698dace2f94d52a73a7e80db0","target":"record","created_at":"2026-07-05T10:53:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a65b2ccfef39d42f33b0866aa5e12793e7938e613ef7244c7326bbd47725a706","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T07:17:59Z","title_canon_sha256":"586b0a13f8b39242fec54dd232cf9532be5eb8fea21f817071daf699eb2dd4b1"},"schema_version":"1.0","source":{"id":"2504.17315","kind":"arxiv","version":1}},"canonical_sha256":"70aa0798418770de1d0cadba3d5ad7f587c341c7946335a7aaf450add6e2c422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70aa0798418770de1d0cadba3d5ad7f587c341c7946335a7aaf450add6e2c422","first_computed_at":"2026-07-05T10:53:26.525095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:26.525095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q9iap0Ixggwq7VilsanVUb96TOochtyIUs/eo0ZP2UYgbOdt8lx9zql1L0hJxUM3ga8m8m2sgZt+elsmEf34Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:26.525584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88592c7caa65e78803426492a7e37163884c31b698dace2f94d52a73a7e80db0","sha256:c5d03b4ad9a5c228ca90c1eb3d5013ce449fa6bde2e8dc66f81029017e746abd"],"state_sha256":"9a7b11cfdd2b2c703c4fc5d482a13c7a0b03c660ee0a5fab244e4d28ee2a9d62"}