{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QROXZGT4RQ74H2K3C7ESA44QCH","short_pith_number":"pith:QROXZGT4","schema_version":"1.0","canonical_sha256":"845d7c9a7c8c3fc3e95b17c920739011dfa7b5625159b67b3bc6f5c23b924d86","source":{"kind":"arxiv","id":"2506.00060","version":1},"attestation_state":"computed","paper":{"title":"Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Ali Yilmaz, Michael Bietenbeck, Sina Amirrajab, Volker Vehof","submitted_at":"2025-05-29T11:25:10Z","abstract_excerpt":"Purpose: We investigated the utilization of privacy-preserving, locally-deployed, open-source Large Language Models (LLMs) to extract diagnostic information from free-text cardiovascular magnetic resonance (CMR) reports. Materials and Methods: We evaluated nine open-source LLMs on their ability to identify diagnoses and classify patients into various cardiac diagnostic categories based on descriptive findings in 109 clinical CMR reports. Performance was quantified using standard classification metrics including accuracy, precision, recall, and F1 score. We also employed confusion matrices to e"},"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":"2506.00060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-29T11:25:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"96922d1991b625a57092a440d0523251f61c254668fcf29a77559f102d5e6832","abstract_canon_sha256":"67b3e1a60447806c8f4e2e2bc8439c8fb7a51e34b7d7006616820111d091c80c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:28.290953Z","signature_b64":"lNfwqUEhWioH2aOtMKYJaM82VHm3hG9FpM6qrE0U+ZfMUN6EjkOH7CloOD9StsSlz6UutihweLP3VsB2m1bUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"845d7c9a7c8c3fc3e95b17c920739011dfa7b5625159b67b3bc6f5c23b924d86","last_reissued_at":"2026-07-05T11:13:28.290426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:28.290426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Ali Yilmaz, Michael Bietenbeck, Sina Amirrajab, Volker Vehof","submitted_at":"2025-05-29T11:25:10Z","abstract_excerpt":"Purpose: We investigated the utilization of privacy-preserving, locally-deployed, open-source Large Language Models (LLMs) to extract diagnostic information from free-text cardiovascular magnetic resonance (CMR) reports. Materials and Methods: We evaluated nine open-source LLMs on their ability to identify diagnoses and classify patients into various cardiac diagnostic categories based on descriptive findings in 109 clinical CMR reports. Performance was quantified using standard classification metrics including accuracy, precision, recall, and F1 score. We also employed confusion matrices to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00060","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/2506.00060/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":"2506.00060","created_at":"2026-07-05T11:13:28.290504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00060v1","created_at":"2026-07-05T11:13:28.290504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00060","created_at":"2026-07-05T11:13:28.290504+00:00"},{"alias_kind":"pith_short_12","alias_value":"QROXZGT4RQ74","created_at":"2026-07-05T11:13:28.290504+00:00"},{"alias_kind":"pith_short_16","alias_value":"QROXZGT4RQ74H2K3","created_at":"2026-07-05T11:13:28.290504+00:00"},{"alias_kind":"pith_short_8","alias_value":"QROXZGT4","created_at":"2026-07-05T11:13:28.290504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08045","citing_title":"Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH","json":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH.json","graph_json":"https://pith.science/api/pith-number/QROXZGT4RQ74H2K3C7ESA44QCH/graph.json","events_json":"https://pith.science/api/pith-number/QROXZGT4RQ74H2K3C7ESA44QCH/events.json","paper":"https://pith.science/paper/QROXZGT4"},"agent_actions":{"view_html":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH","download_json":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH.json","view_paper":"https://pith.science/paper/QROXZGT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00060&json=true","fetch_graph":"https://pith.science/api/pith-number/QROXZGT4RQ74H2K3C7ESA44QCH/graph.json","fetch_events":"https://pith.science/api/pith-number/QROXZGT4RQ74H2K3C7ESA44QCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH/action/storage_attestation","attest_author":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH/action/author_attestation","sign_citation":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH/action/citation_signature","submit_replication":"https://pith.science/pith/QROXZGT4RQ74H2K3C7ESA44QCH/action/replication_record"}},"created_at":"2026-07-05T11:13:28.290504+00:00","updated_at":"2026-07-05T11:13:28.290504+00:00"}