{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NCAM3VY4UKHLLDQZIVZCZYB4ER","short_pith_number":"pith:NCAM3VY4","schema_version":"1.0","canonical_sha256":"6880cdd71ca28eb58e1945722ce03c2470e7ef2caa3e0d68b4a1a83d1a750b07","source":{"kind":"arxiv","id":"2508.08273","version":1},"attestation_state":"computed","paper":{"title":"TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Blaz \\v{S}krlj, Daniela Zaharie, Kristian Miok, Marko Robnik \\v{S}ikonja","submitted_at":"2025-07-30T16:28:10Z","abstract_excerpt":"Clinical language models often struggle to provide trustworthy predictions and explanations when applied to lengthy, unstructured electronic health records (EHRs). This work introduces TT-XAI, a lightweight and effective framework that improves both classification performance and interpretability through domain-aware keyword distillation and reasoning with large language models (LLMs). First, we demonstrate that distilling raw discharge notes into concise keyword representations significantly enhances BERT classifier performance and improves local explanation fidelity via a focused variant of "},"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":"2508.08273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T16:28:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbd6710e0222eb66f152c1a2412375f851e43add40563a682e4dd37d97e90e4f","abstract_canon_sha256":"8017e3b378038c1cd5403b992d4b1306da6775f682346bd6148b624223e43cc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:25.108050Z","signature_b64":"QpBQQNL3vfLrOpUDJwZtl5b/w51b6h3CfB10zYD8Gnmb/yknptjaUVlTme4/Dni4ENBCLhTVhv/0cTqQ9WzkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6880cdd71ca28eb58e1945722ce03c2470e7ef2caa3e0d68b4a1a83d1a750b07","last_reissued_at":"2026-07-05T11:52:25.107597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:25.107597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Blaz \\v{S}krlj, Daniela Zaharie, Kristian Miok, Marko Robnik \\v{S}ikonja","submitted_at":"2025-07-30T16:28:10Z","abstract_excerpt":"Clinical language models often struggle to provide trustworthy predictions and explanations when applied to lengthy, unstructured electronic health records (EHRs). This work introduces TT-XAI, a lightweight and effective framework that improves both classification performance and interpretability through domain-aware keyword distillation and reasoning with large language models (LLMs). First, we demonstrate that distilling raw discharge notes into concise keyword representations significantly enhances BERT classifier performance and improves local explanation fidelity via a focused variant of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08273","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/2508.08273/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":"2508.08273","created_at":"2026-07-05T11:52:25.107655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08273v1","created_at":"2026-07-05T11:52:25.107655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08273","created_at":"2026-07-05T11:52:25.107655+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCAM3VY4UKHL","created_at":"2026-07-05T11:52:25.107655+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCAM3VY4UKHLLDQZ","created_at":"2026-07-05T11:52:25.107655+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCAM3VY4","created_at":"2026-07-05T11:52:25.107655+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/NCAM3VY4UKHLLDQZIVZCZYB4ER","json":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER.json","graph_json":"https://pith.science/api/pith-number/NCAM3VY4UKHLLDQZIVZCZYB4ER/graph.json","events_json":"https://pith.science/api/pith-number/NCAM3VY4UKHLLDQZIVZCZYB4ER/events.json","paper":"https://pith.science/paper/NCAM3VY4"},"agent_actions":{"view_html":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER","download_json":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER.json","view_paper":"https://pith.science/paper/NCAM3VY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08273&json=true","fetch_graph":"https://pith.science/api/pith-number/NCAM3VY4UKHLLDQZIVZCZYB4ER/graph.json","fetch_events":"https://pith.science/api/pith-number/NCAM3VY4UKHLLDQZIVZCZYB4ER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER/action/storage_attestation","attest_author":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER/action/author_attestation","sign_citation":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER/action/citation_signature","submit_replication":"https://pith.science/pith/NCAM3VY4UKHLLDQZIVZCZYB4ER/action/replication_record"}},"created_at":"2026-07-05T11:52:25.107655+00:00","updated_at":"2026-07-05T11:52:25.107655+00:00"}