{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OIT4KSOSYJ2S6G76ID32RQD5UI","short_pith_number":"pith:OIT4KSOS","schema_version":"1.0","canonical_sha256":"7227c549d2c2752f1bfe40f7a8c07da235b624006febfcc341a485dee09525a6","source":{"kind":"arxiv","id":"2605.13464","version":1},"attestation_state":"computed","paper":{"title":"A Unified Three-Stage Machine Learning Framework for Diabetes Detection, Subtype Discrimination, and Cognitive-Metabolic Hypothesis Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A three-stage machine learning framework detects diabetes, clusters subtypes without labels, and links better glycaemic control to higher cognitive scores.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rishav Tewari, Ruzina Haque Laskar, Vishal Pandey","submitted_at":"2026-05-13T12:53:39Z","abstract_excerpt":"Diabetes mellitus affects over 537 million adults worldwide and remains a major challenge in preventive healthcare. Existing machine-learning studies primarily formulate diabetes prediction as a binary classification problem, while subtype-oriented analysis and glycaemic-cognitive associations remain comparatively underexplored. We present a reproducible three-stage machine learning framework for diabetes detection, subtype-oriented clustering, and metabolic-cognitive association analysis. In Stage 1, five supervised classifiers together with a stacking ensemble are benchmarked on the NCSU Dia"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13464","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:53:39Z","cross_cats_sorted":[],"title_canon_sha256":"0b68bdaeaf72940302025077f1101308190a052dbdd74a761e89eb767b55300d","abstract_canon_sha256":"63565e5e2e7b035445ab14a795da3d59adc9bfda21887c076c0afbb5c76942d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.659388Z","signature_b64":"P06lCn+OSZdVx6uJPXbxbiU1lEdWdd4IQhW1UaEyL54/NDaMNoYPslf2B7zE/zxUvtx85FGb1DQB2DhNVB1tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7227c549d2c2752f1bfe40f7a8c07da235b624006febfcc341a485dee09525a6","last_reissued_at":"2026-05-18T02:44:41.658949Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.658949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Three-Stage Machine Learning Framework for Diabetes Detection, Subtype Discrimination, and Cognitive-Metabolic Hypothesis Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A three-stage machine learning framework detects diabetes, clusters subtypes without labels, and links better glycaemic control to higher cognitive scores.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rishav Tewari, Ruzina Haque Laskar, Vishal Pandey","submitted_at":"2026-05-13T12:53:39Z","abstract_excerpt":"Diabetes mellitus affects over 537 million adults worldwide and remains a major challenge in preventive healthcare. Existing machine-learning studies primarily formulate diabetes prediction as a binary classification problem, while subtype-oriented analysis and glycaemic-cognitive associations remain comparatively underexplored. We present a reproducible three-stage machine learning framework for diabetes detection, subtype-oriented clustering, and metabolic-cognitive association analysis. In Stage 1, five supervised classifiers together with a stacking ensemble are benchmarked on the NCSU Dia"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The findings support the utility of statistically grounded and interpretable ML pipelines for reproducible diabetes analytics and subtype-aware exploratory analysis.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the low silhouette score of approximately 0.116 still indicates clinically plausible subtype partitions, and that the NCSU and Ohio datasets are representative without unstated biases affecting predictions or the reported association.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A three-stage ML framework achieves 0.825 ROC-AUC for diabetes detection, identifies two subtypes via clustering on glucose insulin and age, and finds a significant positive correlation (rho=0.208) between glycaemic control and cognitive function.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A three-stage machine learning framework detects diabetes, clusters subtypes without labels, and links better glycaemic control to higher cognitive scores.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3fab5be1054dddbd5603db76e604445aa456f4ebe3e8a5322733bf939a2ffea0"},"source":{"id":"2605.13464","kind":"arxiv","version":1},"verdict":{"id":"c7eee320-3e04-4978-b1e4-d770746733d4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:13:37.682852Z","strongest_claim":"The findings support the utility of statistically grounded and interpretable ML pipelines for reproducible diabetes analytics and subtype-aware exploratory analysis.","one_line_summary":"A three-stage ML framework achieves 0.825 ROC-AUC for diabetes detection, identifies two subtypes via clustering on glucose insulin and age, and finds a significant positive correlation (rho=0.208) between glycaemic control and cognitive function.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the low silhouette score of approximately 0.116 still indicates clinically plausible subtype partitions, and that the NCSU and Ohio datasets are representative without unstated biases affecting predictions or the reported association.","pith_extraction_headline":"A three-stage machine learning framework detects diabetes, clusters subtypes without labels, and links better glycaemic control to higher cognitive scores."},"references":{"count":17,"sample":[{"doi":"","year":2021,"title":"Standards of medical care in diabetes --- 2021","work_id":"c46727f1-93c3-4e11-8063-2a9299bbc683","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"M. A. Atkinson, G. S. Eisenbarth, and A. W. Michels. Type 1 diabetes. The Lancet, 383(9911):69--82, 2014","work_id":"0ceaf2de-8f37-43d8-ba3b-7313076f7c7a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"S. M. de la Monte and J. R. Wands. Alzheimer's disease is type 3 diabetes --- evidence reviewed. Journal of Diabetes Science and Technology, 2(6):1101--1113, 2008","work_id":"4f9be51f-2f1d-45dd-bd6c-864132e1f5b8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"I. Feinkohl, J. F. Price, M. W. Strachan, and B. M. Frier. The impact of diabetes on cognitive decline: potential vascular, metabolic, and psychosocial risk factors. Alzheimer's & Dementia, 11(8):970-","work_id":"f1aab685-a4a5-4393-abf4-e0cf366b4025","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"IDF Diabetes Atlas, 10th ed","work_id":"26f3b479-d39c-44b7-886b-9d4a815e561f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"ae2ad776d1adc89917f167780cb1e6ef343ea743094484b7c351b560249e3813","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fa8dd16ccf8fbb8666d15dafc5c1960a39dc1de682fc2074e5f359441ed5ebaf"},"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":"2605.13464","created_at":"2026-05-18T02:44:41.659013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13464v1","created_at":"2026-05-18T02:44:41.659013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13464","created_at":"2026-05-18T02:44:41.659013+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIT4KSOSYJ2S","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIT4KSOSYJ2S6G76","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIT4KSOS","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI","json":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI.json","graph_json":"https://pith.science/api/pith-number/OIT4KSOSYJ2S6G76ID32RQD5UI/graph.json","events_json":"https://pith.science/api/pith-number/OIT4KSOSYJ2S6G76ID32RQD5UI/events.json","paper":"https://pith.science/paper/OIT4KSOS"},"agent_actions":{"view_html":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI","download_json":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI.json","view_paper":"https://pith.science/paper/OIT4KSOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13464&json=true","fetch_graph":"https://pith.science/api/pith-number/OIT4KSOSYJ2S6G76ID32RQD5UI/graph.json","fetch_events":"https://pith.science/api/pith-number/OIT4KSOSYJ2S6G76ID32RQD5UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI/action/storage_attestation","attest_author":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI/action/author_attestation","sign_citation":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI/action/citation_signature","submit_replication":"https://pith.science/pith/OIT4KSOSYJ2S6G76ID32RQD5UI/action/replication_record"}},"created_at":"2026-05-18T02:44:41.659013+00:00","updated_at":"2026-05-18T02:44:41.659013+00:00"}