{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B2VSHBXRAONI62SFX4CCLKGFH3","short_pith_number":"pith:B2VSHBXR","schema_version":"1.0","canonical_sha256":"0eab2386f1039a8f6a45bf0425a8c53ecd9e2b9dab2f544fc98177056ab7d32a","source":{"kind":"arxiv","id":"2410.12722","version":1},"attestation_state":"computed","paper":{"title":"WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A. Ian Wong, Danielle S. Bitterman, Daphna Idan, David Restrepo, Guergana Savova, Hugo Aerts, Jack Gallifant, Jo\\~ao Matos, Jose M. M. Pascual-Leone, Juan Carlos Climent Pardo, Leo A. Celi, Luis F. Nakayama, Shan Chen, Siena Placino, Takeshi Tohyama, Yingya Li","submitted_at":"2024-10-16T16:31:24Z","abstract_excerpt":"Multimodal/vision language models (VLMs) are increasingly being deployed in healthcare settings worldwide, necessitating robust benchmarks to ensure their safety, efficacy, and fairness. Multiple-choice question and answer (QA) datasets derived from national medical examinations have long served as valuable evaluation tools, but existing datasets are largely text-only and available in a limited subset of languages and countries. To address these challenges, we present WorldMedQA-V, an updated multilingual, multimodal benchmarking dataset designed to evaluate VLMs in healthcare. WorldMedQA-V in"},"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":"2410.12722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T16:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"f4a29df822504fa954af4f70f0714995b51940e3d8be8ba20a1eb8076825d1b8","abstract_canon_sha256":"d14ab49f6910d2c5c7ff6edb81fe1333d76e2172f4f4ae872ddbade2bbbbf47c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:33.040241Z","signature_b64":"BHtE3bXyi17upwhJp/W606NJjQKXx5nUkHB/JQ2dBSHWkoBoJWIkb8siBtSHf9+vRgKohl2KPgDEJbWY5STaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eab2386f1039a8f6a45bf0425a8c53ecd9e2b9dab2f544fc98177056ab7d32a","last_reissued_at":"2026-07-05T09:21:33.039776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:33.039776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A. Ian Wong, Danielle S. Bitterman, Daphna Idan, David Restrepo, Guergana Savova, Hugo Aerts, Jack Gallifant, Jo\\~ao Matos, Jose M. M. Pascual-Leone, Juan Carlos Climent Pardo, Leo A. Celi, Luis F. Nakayama, Shan Chen, Siena Placino, Takeshi Tohyama, Yingya Li","submitted_at":"2024-10-16T16:31:24Z","abstract_excerpt":"Multimodal/vision language models (VLMs) are increasingly being deployed in healthcare settings worldwide, necessitating robust benchmarks to ensure their safety, efficacy, and fairness. Multiple-choice question and answer (QA) datasets derived from national medical examinations have long served as valuable evaluation tools, but existing datasets are largely text-only and available in a limited subset of languages and countries. To address these challenges, we present WorldMedQA-V, an updated multilingual, multimodal benchmarking dataset designed to evaluate VLMs in healthcare. WorldMedQA-V in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12722","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/2410.12722/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":"2410.12722","created_at":"2026-07-05T09:21:33.039829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12722v1","created_at":"2026-07-05T09:21:33.039829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12722","created_at":"2026-07-05T09:21:33.039829+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2VSHBXRAONI","created_at":"2026-07-05T09:21:33.039829+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2VSHBXRAONI62SF","created_at":"2026-07-05T09:21:33.039829+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2VSHBXR","created_at":"2026-07-05T09:21:33.039829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":258,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3","json":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3.json","graph_json":"https://pith.science/api/pith-number/B2VSHBXRAONI62SFX4CCLKGFH3/graph.json","events_json":"https://pith.science/api/pith-number/B2VSHBXRAONI62SFX4CCLKGFH3/events.json","paper":"https://pith.science/paper/B2VSHBXR"},"agent_actions":{"view_html":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3","download_json":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3.json","view_paper":"https://pith.science/paper/B2VSHBXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12722&json=true","fetch_graph":"https://pith.science/api/pith-number/B2VSHBXRAONI62SFX4CCLKGFH3/graph.json","fetch_events":"https://pith.science/api/pith-number/B2VSHBXRAONI62SFX4CCLKGFH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3/action/storage_attestation","attest_author":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3/action/author_attestation","sign_citation":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3/action/citation_signature","submit_replication":"https://pith.science/pith/B2VSHBXRAONI62SFX4CCLKGFH3/action/replication_record"}},"created_at":"2026-07-05T09:21:33.039829+00:00","updated_at":"2026-07-05T09:21:33.039829+00:00"}