{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P62AY7TIKKHYS57DU625EKKFVO","short_pith_number":"pith:P62AY7TI","schema_version":"1.0","canonical_sha256":"7fb40c7e68528f8977e3a7b5d22945ab842769e7b27ebeeeab82f073d9e48617","source":{"kind":"arxiv","id":"2608.00100","version":1},"attestation_state":"computed","paper":{"title":"SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bera Koca, Dania Daye, Ebubechukwu D Enwerem, Emine Meltem, Jacinta Arnold, Kristian Quevada, Mustafa Ege Seker, Pratham Khandelwal, Satvik Tripathi, Shahriar Faghani, Tessa S. Cook","submitted_at":"2026-07-30T20:13:32Z","abstract_excerpt":"Vision-language models (VLMs) are increasingly being evaluated for medical imaging, but many available benchmarks emphasize disease classification, report generation, or broad visual question answering rather than the spatial and anatomical reasoning required for radiology. We developed the Spatial Perception and Anatomical Reasoning in Clinical Radiology (SPARC-Rad) Benchmark, a manually curated multimodal benchmark dataset and evaluation pipeline for assessing these capabilities in radiology VLMs. SPARC-Rad includes 300 image-question pairs derived from healthy control imaging studies in The"},"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":"2608.00100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T20:13:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e5c5bd18f3ba412aa7c5e1683d211ab6482a1229396e247209689d76e5088a88","abstract_canon_sha256":"a4ec22497cc00d18e8d01f5b50f76766853e50f75f49ecbbc400ec4b33efa120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:32:16.309636Z","signature_b64":"/ESrgjHDovv6Lav+aXhX81AaVtfe8PJM/u2N5/2b7VqWk2cM6D1iA/fC67W6DBPsJNn3x9VkGDhcDLbvEydhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fb40c7e68528f8977e3a7b5d22945ab842769e7b27ebeeeab82f073d9e48617","last_reissued_at":"2026-08-04T00:32:16.308154Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:32:16.308154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bera Koca, Dania Daye, Ebubechukwu D Enwerem, Emine Meltem, Jacinta Arnold, Kristian Quevada, Mustafa Ege Seker, Pratham Khandelwal, Satvik Tripathi, Shahriar Faghani, Tessa S. Cook","submitted_at":"2026-07-30T20:13:32Z","abstract_excerpt":"Vision-language models (VLMs) are increasingly being evaluated for medical imaging, but many available benchmarks emphasize disease classification, report generation, or broad visual question answering rather than the spatial and anatomical reasoning required for radiology. We developed the Spatial Perception and Anatomical Reasoning in Clinical Radiology (SPARC-Rad) Benchmark, a manually curated multimodal benchmark dataset and evaluation pipeline for assessing these capabilities in radiology VLMs. SPARC-Rad includes 300 image-question pairs derived from healthy control imaging studies in The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00100","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/2608.00100/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":"2608.00100","created_at":"2026-08-04T00:32:16.309242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00100v1","created_at":"2026-08-04T00:32:16.309242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00100","created_at":"2026-08-04T00:32:16.309242+00:00"},{"alias_kind":"pith_short_12","alias_value":"P62AY7TIKKHY","created_at":"2026-08-04T00:32:16.309242+00:00"},{"alias_kind":"pith_short_16","alias_value":"P62AY7TIKKHYS57D","created_at":"2026-08-04T00:32:16.309242+00:00"},{"alias_kind":"pith_short_8","alias_value":"P62AY7TI","created_at":"2026-08-04T00:32:16.309242+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/P62AY7TIKKHYS57DU625EKKFVO","json":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO.json","graph_json":"https://pith.science/api/pith-number/P62AY7TIKKHYS57DU625EKKFVO/graph.json","events_json":"https://pith.science/api/pith-number/P62AY7TIKKHYS57DU625EKKFVO/events.json","paper":"https://pith.science/paper/P62AY7TI"},"agent_actions":{"view_html":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO","download_json":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO.json","view_paper":"https://pith.science/paper/P62AY7TI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00100&json=true","fetch_graph":"https://pith.science/api/pith-number/P62AY7TIKKHYS57DU625EKKFVO/graph.json","fetch_events":"https://pith.science/api/pith-number/P62AY7TIKKHYS57DU625EKKFVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO/action/storage_attestation","attest_author":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO/action/author_attestation","sign_citation":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO/action/citation_signature","submit_replication":"https://pith.science/pith/P62AY7TIKKHYS57DU625EKKFVO/action/replication_record"}},"created_at":"2026-08-04T00:32:16.309242+00:00","updated_at":"2026-08-04T00:32:16.309242+00:00"}