{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4XXB65XZCC6HCXOYQZ377XJULU","short_pith_number":"pith:4XXB65XZ","schema_version":"1.0","canonical_sha256":"e5ee1f76f910bc715dd88677ffdd345d257b8021bfd5736a2bc6fdf08f2f94e7","source":{"kind":"arxiv","id":"2406.02331","version":1},"attestation_state":"computed","paper":{"title":"Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"ChaeHun Park, Du-Seong Chang, Hyesu Lim, Jaegul Choo, Jaeseok Kim, Junmo Park, Koanho Lee, Yu-Jung Heo","submitted_at":"2024-06-04T14:00:02Z","abstract_excerpt":"Building a reliable visual question answering~(VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that t"},"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":"2406.02331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T14:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"a82360b4e937a2ad294e7535d8bbdf39cf517e08e1650691e146c9a0e8b04329","abstract_canon_sha256":"1f16afdc13e39715d8362d18f5071fef1fd01903412f8cc686d44ad170e86250"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:18.404766Z","signature_b64":"CqT9RVOpztvXf85t9IF9Fuj7ycm5AS58GHPFbmxIQZi5xbg92TZaZm44o/RJkOaQA4zEn91p5xdHR5OMElkiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ee1f76f910bc715dd88677ffdd345d257b8021bfd5736a2bc6fdf08f2f94e7","last_reissued_at":"2026-07-05T08:27:18.404419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:18.404419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"ChaeHun Park, Du-Seong Chang, Hyesu Lim, Jaegul Choo, Jaeseok Kim, Junmo Park, Koanho Lee, Yu-Jung Heo","submitted_at":"2024-06-04T14:00:02Z","abstract_excerpt":"Building a reliable visual question answering~(VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02331","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/2406.02331/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":"2406.02331","created_at":"2026-07-05T08:27:18.404474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02331v1","created_at":"2026-07-05T08:27:18.404474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02331","created_at":"2026-07-05T08:27:18.404474+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XXB65XZCC6H","created_at":"2026-07-05T08:27:18.404474+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XXB65XZCC6HCXOY","created_at":"2026-07-05T08:27:18.404474+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XXB65XZ","created_at":"2026-07-05T08:27:18.404474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11604","citing_title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU","json":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU.json","graph_json":"https://pith.science/api/pith-number/4XXB65XZCC6HCXOYQZ377XJULU/graph.json","events_json":"https://pith.science/api/pith-number/4XXB65XZCC6HCXOYQZ377XJULU/events.json","paper":"https://pith.science/paper/4XXB65XZ"},"agent_actions":{"view_html":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU","download_json":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU.json","view_paper":"https://pith.science/paper/4XXB65XZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02331&json=true","fetch_graph":"https://pith.science/api/pith-number/4XXB65XZCC6HCXOYQZ377XJULU/graph.json","fetch_events":"https://pith.science/api/pith-number/4XXB65XZCC6HCXOYQZ377XJULU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU/action/storage_attestation","attest_author":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU/action/author_attestation","sign_citation":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU/action/citation_signature","submit_replication":"https://pith.science/pith/4XXB65XZCC6HCXOYQZ377XJULU/action/replication_record"}},"created_at":"2026-07-05T08:27:18.404474+00:00","updated_at":"2026-07-05T08:27:18.404474+00:00"}