{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GPVB54JJLZTLV5SZW4EU67SXTR","short_pith_number":"pith:GPVB54JJ","schema_version":"1.0","canonical_sha256":"33ea1ef1295e66baf659b7094f7e579c5d64d733a73779febb7cd3ec95dfb810","source":{"kind":"arxiv","id":"2511.18676","version":2},"attestation_state":"computed","paper":{"title":"MedVision: Benchmarking Quantitative Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Raman Dutt, Sotirios A Tsaftaris, Timothy Hospedales, Yongcheng Yao, Yongshuo Zong, Yongxin Yang","submitted_at":"2025-11-24T01:26:07Z","abstract_excerpt":"Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., \"Is this normal or abnormal?\") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which physicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve "},"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":"2511.18676","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T01:26:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"086bcfad7b7d648c9228f9df7efbd2953a6c17b7bef4ad26914fc0c1ae8ced40","abstract_canon_sha256":"c1c8748cef42c89afaa61dea65815ea7c8b2cab5ac2b4f4a07028b7bfc25ae37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:10.878896Z","signature_b64":"b4Yw8HMN5EN3OJd4IrjJ04wahugRdOExiGDGffkVHPmaGfulQthvEErMSS4NpIv2RxSutDAJE/8GQT6CWQE/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ea1ef1295e66baf659b7094f7e579c5d64d733a73779febb7cd3ec95dfb810","last_reissued_at":"2026-06-09T01:05:10.878457Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:10.878457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedVision: Benchmarking Quantitative Medical Image Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Raman Dutt, Sotirios A Tsaftaris, Timothy Hospedales, Yongcheng Yao, Yongshuo Zong, Yongxin Yang","submitted_at":"2025-11-24T01:26:07Z","abstract_excerpt":"Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., \"Is this normal or abnormal?\") or qualitative descriptive tasks. However, clinical decision-making often relies on quantitative assessments, such as measuring the size of a tumor or the angle of a joint, from which physicians draw their own diagnostic conclusions. This quantitative reasoning capability remains underexplored and poorly supported in existing VLMs. In this work, we introduce MedVision, a large-scale dataset and benchmark specifically designed to evaluate and improve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18676","kind":"arxiv","version":2},"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/2511.18676/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":"2511.18676","created_at":"2026-06-09T01:05:10.878514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18676v2","created_at":"2026-06-09T01:05:10.878514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18676","created_at":"2026-06-09T01:05:10.878514+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPVB54JJLZTL","created_at":"2026-06-09T01:05:10.878514+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPVB54JJLZTLV5SZ","created_at":"2026-06-09T01:05:10.878514+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPVB54JJ","created_at":"2026-06-09T01:05:10.878514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR","json":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR.json","graph_json":"https://pith.science/api/pith-number/GPVB54JJLZTLV5SZW4EU67SXTR/graph.json","events_json":"https://pith.science/api/pith-number/GPVB54JJLZTLV5SZW4EU67SXTR/events.json","paper":"https://pith.science/paper/GPVB54JJ"},"agent_actions":{"view_html":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR","download_json":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR.json","view_paper":"https://pith.science/paper/GPVB54JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18676&json=true","fetch_graph":"https://pith.science/api/pith-number/GPVB54JJLZTLV5SZW4EU67SXTR/graph.json","fetch_events":"https://pith.science/api/pith-number/GPVB54JJLZTLV5SZW4EU67SXTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR/action/storage_attestation","attest_author":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR/action/author_attestation","sign_citation":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR/action/citation_signature","submit_replication":"https://pith.science/pith/GPVB54JJLZTLV5SZW4EU67SXTR/action/replication_record"}},"created_at":"2026-06-09T01:05:10.878514+00:00","updated_at":"2026-06-09T01:05:10.878514+00:00"}