{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:524TYMLLWLRB5LN3FK7VY3CND5","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":"351420134015376496b91d349a1f6e8493f217bb411fec0ba925cec275a33b0b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T14:23:38Z","title_canon_sha256":"0df3a76441dbf990e621775f20bf2420000f3b02742adce5b1525ee06a1b8f52"},"schema_version":"1.0","source":{"id":"2506.11820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11820","created_at":"2026-07-05T11:21:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11820v1","created_at":"2026-07-05T11:21:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11820","created_at":"2026-07-05T11:21:11Z"},{"alias_kind":"pith_short_12","alias_value":"524TYMLLWLRB","created_at":"2026-07-05T11:21:11Z"},{"alias_kind":"pith_short_16","alias_value":"524TYMLLWLRB5LN3","created_at":"2026-07-05T11:21:11Z"},{"alias_kind":"pith_short_8","alias_value":"524TYMLL","created_at":"2026-07-05T11:21:11Z"}],"graph_snapshots":[{"event_id":"sha256:452f2da1c07fe46d32098177800d67cfe0855f5c320315b662d0e0e3ca62a80e","target":"graph","created_at":"2026-07-05T11:21:11Z","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/2506.11820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Translation (VLT) is a challenging task that requires accurately recognizing multilingual text embedded in images and translating it into the target language with the support of visual context. While recent Large Vision-Language Models (LVLMs) have demonstrated strong multilingual and visual understanding capabilities, there is a lack of systematic evaluation and understanding of their performance on VLT. In this work, we present a comprehensive study of VLT from three key perspectives: data quality, model architecture, and evaluation metrics. (1) We identify critical limitatio","authors_text":"Chenyang Lyu, Chris Biemann, Jingheng Pan, Kaifu Zhang, Linlong Xu, Longyue Wang, Minghao Wu, Weihua Luo, Xiaohu Zhao, Xintong Wang, Yixiao Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T14:23:38Z","title":"Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11820","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:b1982e36bfdc3a834ced4f86420125bcd6fa56e9288858fa38fbbe1940c6e82d","target":"record","created_at":"2026-07-05T11:21:11Z","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":"351420134015376496b91d349a1f6e8493f217bb411fec0ba925cec275a33b0b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T14:23:38Z","title_canon_sha256":"0df3a76441dbf990e621775f20bf2420000f3b02742adce5b1525ee06a1b8f52"},"schema_version":"1.0","source":{"id":"2506.11820","kind":"arxiv","version":1}},"canonical_sha256":"eeb93c316bb2e21eadbb2abf5c6c4d1f611b3979d99ca2e560476044e81cb49d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeb93c316bb2e21eadbb2abf5c6c4d1f611b3979d99ca2e560476044e81cb49d","first_computed_at":"2026-07-05T11:21:11.286292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:11.286292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gf3wGi1f54uPReb99ru/QOaA7HmX6Zds8vUacIu/GYUGwItU7+NVvJ+BJuJ7nt6YSBd/S71pelw4C1tj9urBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:11.286780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1982e36bfdc3a834ced4f86420125bcd6fa56e9288858fa38fbbe1940c6e82d","sha256:452f2da1c07fe46d32098177800d67cfe0855f5c320315b662d0e0e3ca62a80e"],"state_sha256":"c71224d85db0165acd53f32bf619fe284587d89db6a090731542d357a9d59c52"}