{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DZP3Z3QCRLTEDB4JQBGWQRMSI2","short_pith_number":"pith:DZP3Z3QC","schema_version":"1.0","canonical_sha256":"1e5fbcee028ae6418789804d68459246bcc9270cd9e3958f8fa6906f82527128","source":{"kind":"arxiv","id":"2606.27264","version":1},"attestation_state":"computed","paper":{"title":"CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anees Ur Rehman Hashmi, Christoph Lippert, Hashmat Shadab Malik, Muzammal Naseer, Numan Saeed, Salman Khan","submitted_at":"2026-06-25T16:47:05Z","abstract_excerpt":"Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be traceable to evidence in the scan. Existing chest CT question-answering datasets compound this by reducing expert radiology reports to answer-only pairs, dropping the reasoning that links findings to conclusions and omitting the patient history clinicians rely on. As a result, reasoning-capable 3D chest CT MLLMs remain o"},"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":"2606.27264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T16:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"967bf0fdcf682ac875b1fc76d7506da1a37b469fcd49b2422ef8452db8f3e4ff","abstract_canon_sha256":"5fd22b06b7279a794e7628c3c9cdae75e08e88cd50b0493980641f1116b94d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:16.833862Z","signature_b64":"tVIaoyhW0CAt7A1Emd/l8qcLxowidCRPmZQTS56dzmiX5Tc3jJDNJWEm6btwcYzbmvUeUlvrSBhYixCwoz5rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5fbcee028ae6418789804d68459246bcc9270cd9e3958f8fa6906f82527128","last_reissued_at":"2026-06-26T01:16:16.833484Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:16.833484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anees Ur Rehman Hashmi, Christoph Lippert, Hashmat Shadab Malik, Muzammal Naseer, Numan Saeed, Salman Khan","submitted_at":"2026-06-25T16:47:05Z","abstract_excerpt":"Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be traceable to evidence in the scan. Existing chest CT question-answering datasets compound this by reducing expert radiology reports to answer-only pairs, dropping the reasoning that links findings to conclusions and omitting the patient history clinicians rely on. As a result, reasoning-capable 3D chest CT MLLMs remain o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27264","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/2606.27264/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":"2606.27264","created_at":"2026-06-26T01:16:16.833539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27264v1","created_at":"2026-06-26T01:16:16.833539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27264","created_at":"2026-06-26T01:16:16.833539+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZP3Z3QCRLTE","created_at":"2026-06-26T01:16:16.833539+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZP3Z3QCRLTEDB4J","created_at":"2026-06-26T01:16:16.833539+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZP3Z3QC","created_at":"2026-06-26T01:16:16.833539+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/DZP3Z3QCRLTEDB4JQBGWQRMSI2","json":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2.json","graph_json":"https://pith.science/api/pith-number/DZP3Z3QCRLTEDB4JQBGWQRMSI2/graph.json","events_json":"https://pith.science/api/pith-number/DZP3Z3QCRLTEDB4JQBGWQRMSI2/events.json","paper":"https://pith.science/paper/DZP3Z3QC"},"agent_actions":{"view_html":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2","download_json":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2.json","view_paper":"https://pith.science/paper/DZP3Z3QC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27264&json=true","fetch_graph":"https://pith.science/api/pith-number/DZP3Z3QCRLTEDB4JQBGWQRMSI2/graph.json","fetch_events":"https://pith.science/api/pith-number/DZP3Z3QCRLTEDB4JQBGWQRMSI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2/action/storage_attestation","attest_author":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2/action/author_attestation","sign_citation":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2/action/citation_signature","submit_replication":"https://pith.science/pith/DZP3Z3QCRLTEDB4JQBGWQRMSI2/action/replication_record"}},"created_at":"2026-06-26T01:16:16.833539+00:00","updated_at":"2026-06-26T01:16:16.833539+00:00"}