{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5TUPF2YVEO6A3VAFZKAUUFVQFE","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":"787ae56fb4f0d1426da2810caac87412fc93b75c7678c1a0808c0d053e4602fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T11:12:39Z","title_canon_sha256":"6a5f11d0d512081ed3962d49e70a047f48796ea3bdbe5ebd5b3decfc5ab25dfe"},"schema_version":"1.0","source":{"id":"2507.11200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11200","created_at":"2026-07-05T11:39:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11200v2","created_at":"2026-07-05T11:39:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11200","created_at":"2026-07-05T11:39:14Z"},{"alias_kind":"pith_short_12","alias_value":"5TUPF2YVEO6A","created_at":"2026-07-05T11:39:14Z"},{"alias_kind":"pith_short_16","alias_value":"5TUPF2YVEO6A3VAF","created_at":"2026-07-05T11:39:14Z"},{"alias_kind":"pith_short_8","alias_value":"5TUPF2YV","created_at":"2026-07-05T11:39:14Z"}],"graph_snapshots":[{"event_id":"sha256:5d3f1cec68d4bc19a3bd31daa2df97273286a28259902fda4ce2cc4d238f3a2c","target":"graph","created_at":"2026-07-05T11:39:14Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.11200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a comprehensive evaluation of open-source general-purpose and medically specialised VLMs, ranging from 3B to 72B parameters, across eight benchmarks: MedXpert, OmniMedVQA, PMC-VQA, PathVQA, MMMU, SLAKE, and VQA-RAD. To observe model performance across different aspects, we first separate it into understanding and reasoning components. Three salient findings emerge. First, large genera","authors_text":"Che Liu, Daniel Rueckert, Jiazhen Pan, Rossella Arcucci, Weixiang Shen, Wenjia Bai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T11:12:39Z","title":"How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11200","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:93f0f04a1068d0de722fb265972f76408f68e1c4b9e57227ec94c2a30909480f","target":"record","created_at":"2026-07-05T11:39:14Z","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":"787ae56fb4f0d1426da2810caac87412fc93b75c7678c1a0808c0d053e4602fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T11:12:39Z","title_canon_sha256":"6a5f11d0d512081ed3962d49e70a047f48796ea3bdbe5ebd5b3decfc5ab25dfe"},"schema_version":"1.0","source":{"id":"2507.11200","kind":"arxiv","version":2}},"canonical_sha256":"ece8f2eb1523bc0dd405ca814a16b02937cf79c35468c12ca944a0f0f1cfd104","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ece8f2eb1523bc0dd405ca814a16b02937cf79c35468c12ca944a0f0f1cfd104","first_computed_at":"2026-07-05T11:39:14.010345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:14.010345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dl4zAZZ95y81ZobgmNJyjH14B7Q9AIrdE8OB5gPodVCWfLywbc4DtxDEbxpNboAn0alt4gZRG6M8+GVc8At2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:14.010807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93f0f04a1068d0de722fb265972f76408f68e1c4b9e57227ec94c2a30909480f","sha256:5d3f1cec68d4bc19a3bd31daa2df97273286a28259902fda4ce2cc4d238f3a2c"],"state_sha256":"b396d281660838eeb8b8c07f9a0961fd78543a251a356652a9e93279c7005cd4"}