{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UE3ZENLFBQ7VZIZHIIT7SOX3YN","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":"4456ba3b781fa4a49c1a4c2f0c19acb4691cddbeeffaa6128b348edd2e531ff3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:27:42Z","title_canon_sha256":"2fa1a785fad02dd34aa6179a7de8086e669e520f3ee73001872b90bf6ba49cc6"},"schema_version":"1.0","source":{"id":"2606.02809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02809","created_at":"2026-06-03T01:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02809v1","created_at":"2026-06-03T01:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02809","created_at":"2026-06-03T01:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"UE3ZENLFBQ7V","created_at":"2026-06-03T01:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"UE3ZENLFBQ7VZIZH","created_at":"2026-06-03T01:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"UE3ZENLF","created_at":"2026-06-03T01:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:2d6c687e481f0871f840ba0623f5747768e170a77e3566291ecc21cc65e437c9","target":"graph","created_at":"2026-06-03T01:05:23Z","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/2606.02809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating vision-language models (VLMs) on medical images requires benchmarks that are clinically grounded, scalable, and controlled for evaluation confounds. Existing public benchmarks are limited in scale, manually annotated, or potentially leaked into VLM pretraining corpora. We present an automated agent-driven pipeline that generates multiple-choice VQA datasets directly from paired private radiology reports and 3D oncology imaging, producing two complementary question types: RADS-style questions deterministically derived from clinician-defined reporting schemas, and radiology report-der","authors_text":"Bo Liu, Hanxue Gu, Hui Lin, Jacob Ellison, Janine M. Lupo, Kang Wang, Xiangru Li, Yang Yang, Zheren Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:27:42Z","title":"Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical Imaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02809","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:d6a7f17b42fb820f8cb28ffd2f5c306f536deb1a7ca8cbc718b9e41c48c0bff2","target":"record","created_at":"2026-06-03T01:05:23Z","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":"4456ba3b781fa4a49c1a4c2f0c19acb4691cddbeeffaa6128b348edd2e531ff3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:27:42Z","title_canon_sha256":"2fa1a785fad02dd34aa6179a7de8086e669e520f3ee73001872b90bf6ba49cc6"},"schema_version":"1.0","source":{"id":"2606.02809","kind":"arxiv","version":1}},"canonical_sha256":"a1379235650c3f5ca3274227f93afbc34c33acdde20706b89b003ccb15db6abe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1379235650c3f5ca3274227f93afbc34c33acdde20706b89b003ccb15db6abe","first_computed_at":"2026-06-03T01:05:23.590998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:23.590998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AvGes3Wbh6Rk1ui7XZrr+/jt5/dPs2PEcrn8YHGMGfS0G2DBD0fW067tdOUjnaHgRp2Ua0jXYCR3DJb7S1SJAQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:23.591380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6a7f17b42fb820f8cb28ffd2f5c306f536deb1a7ca8cbc718b9e41c48c0bff2","sha256:2d6c687e481f0871f840ba0623f5747768e170a77e3566291ecc21cc65e437c9"],"state_sha256":"0050ada1b458a26bba38542b0e66e37bda59a2a01801250ae785e6d3bc4f7312"}