{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YFUAIQLKJP5SB7VT5V2DHF3FCR","short_pith_number":"pith:YFUAIQLK","canonical_record":{"source":{"id":"2505.24173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"4d293d4e496c78131185afdc17e54116ad1701d7196f43d9796982b4beab57d5","abstract_canon_sha256":"c1bcee55dfa46b29e4064d0f1c84e056bad0eef1be3d8879ea266257e01c16ec"},"schema_version":"1.0"},"canonical_sha256":"c16804416a4bfb20feb3ed743397651451833e614fdbddb2adfdf8753e98fa04","source":{"kind":"arxiv","id":"2505.24173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24173","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24173v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24173","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"YFUAIQLKJP5S","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"YFUAIQLKJP5SB7VT","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"YFUAIQLK","created_at":"2026-07-05T11:12:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YFUAIQLKJP5SB7VT5V2DHF3FCR","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"4d293d4e496c78131185afdc17e54116ad1701d7196f43d9796982b4beab57d5","abstract_canon_sha256":"c1bcee55dfa46b29e4064d0f1c84e056bad0eef1be3d8879ea266257e01c16ec"},"schema_version":"1.0"},"canonical_sha256":"c16804416a4bfb20feb3ed743397651451833e614fdbddb2adfdf8753e98fa04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:43.371261Z","signature_b64":"3ChBZzFeNjYBdLtZ17iPl74tmTJSstTfoayt6QnOOBF301NdaV/lLw+uiqasirjlnKM+jc6VDpUNIABAjec6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c16804416a4bfb20feb3ed743397651451833e614fdbddb2adfdf8753e98fa04","last_reissued_at":"2026-07-05T11:12:43.370771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:43.370771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24173","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0anvyzKV5zihU6WvpLDCjZCWnOsb6JSqoxHW2JYD7RX16bXuffVjRaHkAXftp3/EoJufMr4fOYZUo0kkCwxsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:38:19.406836Z"},"content_sha256":"6c122e1e2e2abbf03f72842de0ed03027448d2582f0dd89d549fb3cbbc268995","schema_version":"1.0","event_id":"sha256:6c122e1e2e2abbf03f72842de0ed03027448d2582f0dd89d549fb3cbbc268995"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YFUAIQLKJP5SB7VT5V2DHF3FCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuxi Xiao, Haiyang Bian, Lei Wei, Tianhong Zhou, Xuegong Zhang, Yingtao Zhu, Yin Xu","submitted_at":"2025-05-30T03:33:25Z","abstract_excerpt":"Vision-language models (VLMs) exhibit strong zero-shot generalization on natural images and show early promise in interpretable medical image analysis. However, existing benchmarks do not systematically evaluate whether these models truly reason like human clinicians or merely imitate superficial patterns. To address this gap, we propose DrVD-Bench, the first multimodal benchmark for clinical visual reasoning. DrVD-Bench consists of three modules: Visual Evidence Comprehension, Reasoning Trajectory Assessment, and Report Generation Evaluation, comprising a total of 7,789 image-question pairs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24173","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/2505.24173/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oEk1KJyvrllOIsY2REI4LEwJZ4XO+aqEE9M185oH8ob/3Lf7oeTkFw09GW5JNRedHCPAOqqbcrEFkM03onZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:38:19.407196Z"},"content_sha256":"aff2d02d81e16c3cbb23dc505dcd18dc05383bf8f046cab9d1135a1f68480701","schema_version":"1.0","event_id":"sha256:aff2d02d81e16c3cbb23dc505dcd18dc05383bf8f046cab9d1135a1f68480701"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/bundle.json","state_url":"https://pith.science/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T23:38:19Z","links":{"resolver":"https://pith.science/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR","bundle":"https://pith.science/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/bundle.json","state":"https://pith.science/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFUAIQLKJP5SB7VT5V2DHF3FCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YFUAIQLKJP5SB7VT5V2DHF3FCR","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":"c1bcee55dfa46b29e4064d0f1c84e056bad0eef1be3d8879ea266257e01c16ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:33:25Z","title_canon_sha256":"4d293d4e496c78131185afdc17e54116ad1701d7196f43d9796982b4beab57d5"},"schema_version":"1.0","source":{"id":"2505.24173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24173","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24173v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24173","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"YFUAIQLKJP5S","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"YFUAIQLKJP5SB7VT","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"YFUAIQLK","created_at":"2026-07-05T11:12:43Z"}],"graph_snapshots":[{"event_id":"sha256:aff2d02d81e16c3cbb23dc505dcd18dc05383bf8f046cab9d1135a1f68480701","target":"graph","created_at":"2026-07-05T11:12:43Z","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/2505.24173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) exhibit strong zero-shot generalization on natural images and show early promise in interpretable medical image analysis. However, existing benchmarks do not systematically evaluate whether these models truly reason like human clinicians or merely imitate superficial patterns. To address this gap, we propose DrVD-Bench, the first multimodal benchmark for clinical visual reasoning. DrVD-Bench consists of three modules: Visual Evidence Comprehension, Reasoning Trajectory Assessment, and Report Generation Evaluation, comprising a total of 7,789 image-question pairs. ","authors_text":"Chuxi Xiao, Haiyang Bian, Lei Wei, Tianhong Zhou, Xuegong Zhang, Yingtao Zhu, Yin Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:33:25Z","title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24173","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":"sha256:6c122e1e2e2abbf03f72842de0ed03027448d2582f0dd89d549fb3cbbc268995","target":"record","created_at":"2026-07-05T11:12:43Z","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":"c1bcee55dfa46b29e4064d0f1c84e056bad0eef1be3d8879ea266257e01c16ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:33:25Z","title_canon_sha256":"4d293d4e496c78131185afdc17e54116ad1701d7196f43d9796982b4beab57d5"},"schema_version":"1.0","source":{"id":"2505.24173","kind":"arxiv","version":1}},"canonical_sha256":"c16804416a4bfb20feb3ed743397651451833e614fdbddb2adfdf8753e98fa04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c16804416a4bfb20feb3ed743397651451833e614fdbddb2adfdf8753e98fa04","first_computed_at":"2026-07-05T11:12:43.370771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:43.370771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ChBZzFeNjYBdLtZ17iPl74tmTJSstTfoayt6QnOOBF301NdaV/lLw+uiqasirjlnKM+jc6VDpUNIABAjec6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:43.371261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c122e1e2e2abbf03f72842de0ed03027448d2582f0dd89d549fb3cbbc268995","sha256:aff2d02d81e16c3cbb23dc505dcd18dc05383bf8f046cab9d1135a1f68480701"],"state_sha256":"96c7c1fe6e48bd56d0105753aad87ec1eb16e3bbd587f2ee6cacd9975830524b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8sysEj1EGbmFedu6WkXGa5Ny2VdZONw1udiw6/ATxuHIZzSpZhIkaxomsZFJALPm2vzbu6iKyZP9XbjtUbXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:38:19.409083Z","bundle_sha256":"f3ef9db27abee06c5b1a6cbf920000753e85dec9a2ee4d82d1a04f855cffbd2c"}}