{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MVKFNPNECPZ6JR5XBUWTJG63VQ","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":"c2b0f2e003a52f7c2409c4068c3728b8b11c172cc67629ed6c64fd48c88ca946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T09:50:19Z","title_canon_sha256":"9d0b42e6abea74530dcb5ed41d6fd980f45f94ff6d34e854f2d87a6dd3b0e1fa"},"schema_version":"1.0","source":{"id":"2605.24492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24492","created_at":"2026-05-26T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24492v1","created_at":"2026-05-26T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24492","created_at":"2026-05-26T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"MVKFNPNECPZ6","created_at":"2026-05-26T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"MVKFNPNECPZ6JR5X","created_at":"2026-05-26T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"MVKFNPNE","created_at":"2026-05-26T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:c4b4263e7bf5914a5573398ff6694d155812e1098b93723a82ac8f8b3b2e82c4","target":"graph","created_at":"2026-05-26T01:03:42Z","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/2605.24492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test rob","authors_text":"Fucheng Niu, Jiaxiang Liu, Wen Ma, Zhiting Fan, Zikai Xiao, Zuozhu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T09:50:19Z","title":"Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24492","kind":"arxiv","version":1},"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":"sha256:23eac8cf9c2e1ce41b07a97dff00ea78a936c88edc70b379086902ace6f24e38","target":"record","created_at":"2026-05-26T01:03:42Z","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":"c2b0f2e003a52f7c2409c4068c3728b8b11c172cc67629ed6c64fd48c88ca946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T09:50:19Z","title_canon_sha256":"9d0b42e6abea74530dcb5ed41d6fd980f45f94ff6d34e854f2d87a6dd3b0e1fa"},"schema_version":"1.0","source":{"id":"2605.24492","kind":"arxiv","version":1}},"canonical_sha256":"655456bda413f3e4c7b70d2d349bdbac1223ec67e9fc590d92897730be35d339","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"655456bda413f3e4c7b70d2d349bdbac1223ec67e9fc590d92897730be35d339","first_computed_at":"2026-05-26T01:03:42.737917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:42.737917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"87pwl2jv3G+OfIcWICkqBMWRkKEcuSQ7JTEaP0MTNvhT9DsWQGv6k9HPGK4AKaECieXU2dIl9aZNvjZ6L8xiDw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:42.738677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23eac8cf9c2e1ce41b07a97dff00ea78a936c88edc70b379086902ace6f24e38","sha256:c4b4263e7bf5914a5573398ff6694d155812e1098b93723a82ac8f8b3b2e82c4"],"state_sha256":"65cedd4af48931fc57d80482b69d9c6dd20db34188fea238ddac8dd9916b90a7"}