{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MMUELQVFFGG4VTQMJYXN26WLOT","short_pith_number":"pith:MMUELQVF","schema_version":"1.0","canonical_sha256":"632845c2a5298dcace0c4e2edd7acb74c4e2877789f2a9734f92324a7dc542e2","source":{"kind":"arxiv","id":"2505.07162","version":1},"attestation_state":"computed","paper":{"title":"KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hajar Sakai, Sarah S. Lam","submitted_at":"2025-05-12T00:58:25Z","abstract_excerpt":"The increasing volume of healthcare textual data requires computationally efficient, yet highly accurate classification approaches able to handle the nuanced and complex nature of medical terminology. This research presents Knowledge Distillation for Healthcare Multi-Label Text Classification (KDH-MLTC), a framework leveraging model compression and Large Language Models (LLMs). The proposed approach addresses conventional healthcare Multi-Label Text Classification (MLTC) challenges by integrating knowledge distillation and sequential fine-tuning, subsequently optimized through Particle Swarm 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":"2505.07162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T00:58:25Z","cross_cats_sorted":[],"title_canon_sha256":"8c8613155b2255f990cafb817502777b51a43a70d1181b41d68bae2e1060dd3e","abstract_canon_sha256":"95c21b59609e653cf96fdf8c5ed17e4c275b1cd91cd97a5f0f14006a74a55974"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:43.459047Z","signature_b64":"EjPtTB1jeqCdqHtzgVChL/7YJVp0i935H6gnnr+MAYWHmPBb9tYTHljeVlOzpRy8DBWoSPZvBpujEoo5ou9qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632845c2a5298dcace0c4e2edd7acb74c4e2877789f2a9734f92324a7dc542e2","last_reissued_at":"2026-07-05T11:01:43.458580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:43.458580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hajar Sakai, Sarah S. Lam","submitted_at":"2025-05-12T00:58:25Z","abstract_excerpt":"The increasing volume of healthcare textual data requires computationally efficient, yet highly accurate classification approaches able to handle the nuanced and complex nature of medical terminology. This research presents Knowledge Distillation for Healthcare Multi-Label Text Classification (KDH-MLTC), a framework leveraging model compression and Large Language Models (LLMs). The proposed approach addresses conventional healthcare Multi-Label Text Classification (MLTC) challenges by integrating knowledge distillation and sequential fine-tuning, subsequently optimized through Particle Swarm O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07162","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/2505.07162/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":"2505.07162","created_at":"2026-07-05T11:01:43.458637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07162v1","created_at":"2026-07-05T11:01:43.458637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07162","created_at":"2026-07-05T11:01:43.458637+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMUELQVFFGG4","created_at":"2026-07-05T11:01:43.458637+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMUELQVFFGG4VTQM","created_at":"2026-07-05T11:01:43.458637+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMUELQVF","created_at":"2026-07-05T11:01:43.458637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.09722","citing_title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT","json":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT.json","graph_json":"https://pith.science/api/pith-number/MMUELQVFFGG4VTQMJYXN26WLOT/graph.json","events_json":"https://pith.science/api/pith-number/MMUELQVFFGG4VTQMJYXN26WLOT/events.json","paper":"https://pith.science/paper/MMUELQVF"},"agent_actions":{"view_html":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT","download_json":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT.json","view_paper":"https://pith.science/paper/MMUELQVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07162&json=true","fetch_graph":"https://pith.science/api/pith-number/MMUELQVFFGG4VTQMJYXN26WLOT/graph.json","fetch_events":"https://pith.science/api/pith-number/MMUELQVFFGG4VTQMJYXN26WLOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT/action/storage_attestation","attest_author":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT/action/author_attestation","sign_citation":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT/action/citation_signature","submit_replication":"https://pith.science/pith/MMUELQVFFGG4VTQMJYXN26WLOT/action/replication_record"}},"created_at":"2026-07-05T11:01:43.458637+00:00","updated_at":"2026-07-05T11:01:43.458637+00:00"}