{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5WKWUVIIBMRCA3TGGWEMV2LHYP","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":"0ff197cb4b122f311fd9103f89506e2288bc74cba2f1115d0bd45e54eb7e8c97","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-03T19:55:06Z","title_canon_sha256":"3dffca7dbaa344ceadcfa408a691b5398bf9917b46db05d0c88f2affc4f09894"},"schema_version":"1.0","source":{"id":"2605.02035","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02035","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02035v2","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02035","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"5WKWUVIIBMRC","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"5WKWUVIIBMRCA3TG","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"5WKWUVII","created_at":"2026-05-27T01:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:cdc0b1054fda94d69d79237d45d93affa7f081d20a9739db3314af6f9bd12f43","target":"graph","created_at":"2026-05-27T01:05:55Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"45d78a49e96f52ec49566ea228aa1360ac9e806f57d6c7e59f784d555163599a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5b995bf02bef8dd03296afbe046b5d0e1e12a55d5deead78cb0cac7ca1047b94"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.02035/integrity.json","findings":[],"snapshot_sha256":"6bd1cb08b84c182faf38354fa4024e5ef63580432218a28d66528a0d0b313047","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chris Biemann, Jingheng Pan, Liang Ding, Longyue Wang, Weihua Luo, Xintong Wang","cross_cats":["cs.AI"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-03T19:55:06Z","title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02035","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T19:29:55.976722Z","id":"da5efd4c-ebc8-44bd-9337-ebb4d4fafd59","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"da5efd4c-ebc8-44bd-9337-ebb4d4fafd59"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b460d740ca82a11d5cf7dee57db31b74ffb1289f3a3f64acc1c34393fd8c90c1","target":"record","created_at":"2026-05-27T01:05:55Z","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":"0ff197cb4b122f311fd9103f89506e2288bc74cba2f1115d0bd45e54eb7e8c97","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-03T19:55:06Z","title_canon_sha256":"3dffca7dbaa344ceadcfa408a691b5398bf9917b46db05d0c88f2affc4f09894"},"schema_version":"1.0","source":{"id":"2605.02035","kind":"arxiv","version":2}},"canonical_sha256":"ed956a55080b22206e663588cae967c3efd4ec7a78fc037fad5db02071830c2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed956a55080b22206e663588cae967c3efd4ec7a78fc037fad5db02071830c2a","first_computed_at":"2026-05-27T01:05:55.900371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:55.900371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5Ms479b7nP3pOTI+i/atXRGV0gNw7V8kEdW7i/spBpksCnD/YOKt6KRO+VS5I4uVCnSvwWhBYDtSDcRfC+qBQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:55.901153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02035","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b460d740ca82a11d5cf7dee57db31b74ffb1289f3a3f64acc1c34393fd8c90c1","sha256:cdc0b1054fda94d69d79237d45d93affa7f081d20a9739db3314af6f9bd12f43"],"state_sha256":"304a908d51748ca690df9a0c487c13e9caf4762c352d487e3355d5341969d95b"}