{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5WKWUVIIBMRCA3TGGWEMV2LHYP","short_pith_number":"pith:5WKWUVII","schema_version":"1.0","canonical_sha256":"ed956a55080b22206e663588cae967c3efd4ec7a78fc037fad5db02071830c2a","source":{"kind":"arxiv","id":"2605.02035","version":2},"attestation_state":"computed","paper":{"title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A dataset of 2,500 translation instances shows that chain-of-thought fine-tuning helps models use visual evidence to resolve ambiguities more consistently.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Jingheng Pan, Liang Ding, Longyue Wang, Weihua Luo, Xintong Wang","submitted_at":"2026-05-03T19:55:06Z","abstract_excerpt":"Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed disambiguation-oriented benchmarks probing the role of vision, we observe that existing benchmarks remain limited by task-format mismatch, narrow ambiguity coverage, or insufficient visual-dependency validation. Moreover, existing ambiguity evaluations are not well suited to diverse ambiguity types in open-ended translation. To address these limitations, we present VIDA (Visual"},"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":true},"canonical_record":{"source":{"id":"2605.02035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-03T19:55:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dffca7dbaa344ceadcfa408a691b5398bf9917b46db05d0c88f2affc4f09894","abstract_canon_sha256":"0ff197cb4b122f311fd9103f89506e2288bc74cba2f1115d0bd45e54eb7e8c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:55.901153Z","signature_b64":"P5Ms479b7nP3pOTI+i/atXRGV0gNw7V8kEdW7i/spBpksCnD/YOKt6KRO+VS5I4uVCnSvwWhBYDtSDcRfC+qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed956a55080b22206e663588cae967c3efd4ec7a78fc037fad5db02071830c2a","last_reissued_at":"2026-05-27T01:05:55.900371Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:55.900371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A dataset of 2,500 translation instances shows that chain-of-thought fine-tuning helps models use visual evidence to resolve ambiguities more consistently.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Jingheng Pan, Liang Ding, Longyue Wang, Weihua Luo, Xintong Wang","submitted_at":"2026-05-03T19:55:06Z","abstract_excerpt":"Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed disambiguation-oriented benchmarks probing the role of vision, we observe that existing benchmarks remain limited by task-format mismatch, narrow ambiguity coverage, or insufficient visual-dependency validation. Moreover, existing ambiguity evaluations are not well suited to diverse ambiguity types in open-ended translation. To address these limitations, we present VIDA (Visual"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments with two state-of-the-art Large Vision Language Models under vanilla inference, supervised fine-tuning (SFT), and our chain-of-thought SFT (CoT-SFT) show that while SFT improves overall translation quality, CoT-SFT yields more consistent gains in disambiguation accuracy, especially on out-of-distribution subsets, indicating a stronger generalization for resolving diverse ambiguity types.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 2,500 instances are accurately annotated such that visual evidence is genuinely required to resolve each ambiguous span, and the LLM-as-a-judge classifier reliably measures correct span-level disambiguation without its own biases or errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VIDA provides 2,500 visually-dependent ambiguous MT instances and LLM-judge metrics; chain-of-thought SFT improves disambiguation accuracy over standard SFT, especially out-of-distribution.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A dataset of 2,500 translation instances shows that chain-of-thought fine-tuning helps models use visual evidence to resolve ambiguities more consistently.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"45d78a49e96f52ec49566ea228aa1360ac9e806f57d6c7e59f784d555163599a"},"source":{"id":"2605.02035","kind":"arxiv","version":2},"verdict":{"id":"da5efd4c-ebc8-44bd-9337-ebb4d4fafd59","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T19:29:55.976722Z","strongest_claim":"Experiments with two state-of-the-art Large Vision Language Models under vanilla inference, supervised fine-tuning (SFT), and our chain-of-thought SFT (CoT-SFT) show that while SFT improves overall translation quality, CoT-SFT yields more consistent gains in disambiguation accuracy, especially on out-of-distribution subsets, indicating a stronger generalization for resolving diverse ambiguity types.","one_line_summary":"VIDA provides 2,500 visually-dependent ambiguous MT instances and LLM-judge metrics; chain-of-thought SFT improves disambiguation accuracy over standard SFT, especially out-of-distribution.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 2,500 instances are accurately annotated such that visual evidence is genuinely required to resolve each ambiguous span, and the LLM-as-a-judge classifier reliably measures correct span-level disambiguation without its own biases or errors.","pith_extraction_headline":"A dataset of 2,500 translation instances shows that chain-of-thought fine-tuning helps models use visual evidence to resolve ambiguities more consistently."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02035/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T16:39:38.586407Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T04:31:22.159965Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:46:45.028012Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6bd1cb08b84c182faf38354fa4024e5ef63580432218a28d66528a0d0b313047"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b995bf02bef8dd03296afbe046b5d0e1e12a55d5deead78cb0cac7ca1047b94"},"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":"2605.02035","created_at":"2026-05-27T01:05:55.900514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.02035v2","created_at":"2026-05-27T01:05:55.900514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02035","created_at":"2026-05-27T01:05:55.900514+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WKWUVIIBMRC","created_at":"2026-05-27T01:05:55.900514+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WKWUVIIBMRCA3TG","created_at":"2026-05-27T01:05:55.900514+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WKWUVII","created_at":"2026-05-27T01:05:55.900514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP","json":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP.json","graph_json":"https://pith.science/api/pith-number/5WKWUVIIBMRCA3TGGWEMV2LHYP/graph.json","events_json":"https://pith.science/api/pith-number/5WKWUVIIBMRCA3TGGWEMV2LHYP/events.json","paper":"https://pith.science/paper/5WKWUVII"},"agent_actions":{"view_html":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP","download_json":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP.json","view_paper":"https://pith.science/paper/5WKWUVII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.02035&json=true","fetch_graph":"https://pith.science/api/pith-number/5WKWUVIIBMRCA3TGGWEMV2LHYP/graph.json","fetch_events":"https://pith.science/api/pith-number/5WKWUVIIBMRCA3TGGWEMV2LHYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP/action/storage_attestation","attest_author":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP/action/author_attestation","sign_citation":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP/action/citation_signature","submit_replication":"https://pith.science/pith/5WKWUVIIBMRCA3TGGWEMV2LHYP/action/replication_record"}},"created_at":"2026-05-27T01:05:55.900514+00:00","updated_at":"2026-05-27T01:05:55.900514+00:00"}