{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6YQ5JEEOFLZJC37OR4UVIAUKP7","short_pith_number":"pith:6YQ5JEEO","canonical_record":{"source":{"id":"2502.05638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T16:44:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb2be58a9a8ec76ec66bf7c77109ef3278d3a09b7da092277bc4563bcdad0bb1","abstract_canon_sha256":"11de7528bde0556848e229ed45a2e27cb85c84f5d887a402463ec38b2fd34ac8"},"schema_version":"1.0"},"canonical_sha256":"f621d4908e2af2916fee8f2954028a7fe1c4b3b620438cb8d01919b54f88cfcd","source":{"kind":"arxiv","id":"2502.05638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05638","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05638v1","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05638","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"6YQ5JEEOFLZJ","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"6YQ5JEEOFLZJC37O","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"6YQ5JEEO","created_at":"2026-07-05T11:33:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6YQ5JEEOFLZJC37OR4UVIAUKP7","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T16:44:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb2be58a9a8ec76ec66bf7c77109ef3278d3a09b7da092277bc4563bcdad0bb1","abstract_canon_sha256":"11de7528bde0556848e229ed45a2e27cb85c84f5d887a402463ec38b2fd34ac8"},"schema_version":"1.0"},"canonical_sha256":"f621d4908e2af2916fee8f2954028a7fe1c4b3b620438cb8d01919b54f88cfcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:19.673536Z","signature_b64":"IGhucOlpQlUWXd8r0H3ih+omXJBKiNd9o5966OVPptN5P1yry0mNEIS/J8RmSRpHHi+pBS1nbfv9p6AiqCTyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f621d4908e2af2916fee8f2954028a7fe1c4b3b620438cb8d01919b54f88cfcd","last_reissued_at":"2026-07-05T11:33:19.673026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:19.673026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05638","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":"2026-07-05T11:33:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpK7NqRksscFAZmXBBuUuoPCCboYMRSpZg9v1IkIvOhfYTUbbJyhDvufajCc+c1NoppWFcWktOY64uSy6c3dBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:57:11.322744Z"},"content_sha256":"460c6a78640b4a7a05107f4a6af77f8ac82ea0b3cbe1386a042c79a7e64bf2e8","schema_version":"1.0","event_id":"sha256:460c6a78640b4a7a05107f4a6af77f8ac82ea0b3cbe1386a042c79a7e64bf2e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6YQ5JEEOFLZJC37OR4UVIAUKP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aynur Guluzade, Carlos A Velasco, Florim Hamiti, Jahid Hasan Polash, Naguib Heiba, Yehya Mohamad, Zeyd Boukhers","submitted_at":"2025-02-08T16:44:56Z","abstract_excerpt":"Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the results of our project, which aims to leverage Large Language Models (LLMs) to extract structured information from unstructured clinical reports, focusing on patient history, diagnoses, treatments, and other predefined categories. We developed a workflow with a user interface and evaluated LLMs of varying sizes through prompting strategies and fine-tuning. Our results show that fine-tuned smaller models match or sur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05638","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/2502.05638/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":"2026-07-05T11:33:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KbzoVdlGLHiHW9Ip2ONbHppKu0vxaqCq6Ny/v3gks6mwSzPMeElozbz74l1GRHw01K95L+5JYG38gDLwHypBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:57:11.323810Z"},"content_sha256":"dec00a1d4934508f76302274145fd88b747569bc0509dad96a27f884bc066b0b","schema_version":"1.0","event_id":"sha256:dec00a1d4934508f76302274145fd88b747569bc0509dad96a27f884bc066b0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/bundle.json","state_url":"https://pith.science/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/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":"2026-08-09T06:57:11Z","links":{"resolver":"https://pith.science/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7","bundle":"https://pith.science/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/bundle.json","state":"https://pith.science/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YQ5JEEOFLZJC37OR4UVIAUKP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6YQ5JEEOFLZJC37OR4UVIAUKP7","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":"11de7528bde0556848e229ed45a2e27cb85c84f5d887a402463ec38b2fd34ac8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T16:44:56Z","title_canon_sha256":"cb2be58a9a8ec76ec66bf7c77109ef3278d3a09b7da092277bc4563bcdad0bb1"},"schema_version":"1.0","source":{"id":"2502.05638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05638","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05638v1","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05638","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"6YQ5JEEOFLZJ","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"6YQ5JEEOFLZJC37O","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"6YQ5JEEO","created_at":"2026-07-05T11:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:dec00a1d4934508f76302274145fd88b747569bc0509dad96a27f884bc066b0b","target":"graph","created_at":"2026-07-05T11:33:19Z","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/2502.05638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the results of our project, which aims to leverage Large Language Models (LLMs) to extract structured information from unstructured clinical reports, focusing on patient history, diagnoses, treatments, and other predefined categories. We developed a workflow with a user interface and evaluated LLMs of varying sizes through prompting strategies and fine-tuning. Our results show that fine-tuned smaller models match or sur","authors_text":"Aynur Guluzade, Carlos A Velasco, Florim Hamiti, Jahid Hasan Polash, Naguib Heiba, Yehya Mohamad, Zeyd Boukhers","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T16:44:56Z","title":"ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05638","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":"sha256:460c6a78640b4a7a05107f4a6af77f8ac82ea0b3cbe1386a042c79a7e64bf2e8","target":"record","created_at":"2026-07-05T11:33:19Z","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":"11de7528bde0556848e229ed45a2e27cb85c84f5d887a402463ec38b2fd34ac8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T16:44:56Z","title_canon_sha256":"cb2be58a9a8ec76ec66bf7c77109ef3278d3a09b7da092277bc4563bcdad0bb1"},"schema_version":"1.0","source":{"id":"2502.05638","kind":"arxiv","version":1}},"canonical_sha256":"f621d4908e2af2916fee8f2954028a7fe1c4b3b620438cb8d01919b54f88cfcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f621d4908e2af2916fee8f2954028a7fe1c4b3b620438cb8d01919b54f88cfcd","first_computed_at":"2026-07-05T11:33:19.673026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:19.673026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IGhucOlpQlUWXd8r0H3ih+omXJBKiNd9o5966OVPptN5P1yry0mNEIS/J8RmSRpHHi+pBS1nbfv9p6AiqCTyBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:19.673536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:460c6a78640b4a7a05107f4a6af77f8ac82ea0b3cbe1386a042c79a7e64bf2e8","sha256:dec00a1d4934508f76302274145fd88b747569bc0509dad96a27f884bc066b0b"],"state_sha256":"b1aa5eec825c24d26cd47c9c932d1e099f1c6cef3745805b01d79df1c059fe48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rzv/YLxoXM3xZ5FwSwkqXM3MgQQP/CzyUpK3WZtQfjDFvJB099N0qVHRY0M7hFY4DGuahV807iK+hO+c4KXAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:57:11.384104Z","bundle_sha256":"9760ffbf09537313946433f481632a53ee166199f7a3f6499ed5a490c3c19795"}}