{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PSDR4ZBO5WO7WI3P4QCKS55ZAJ","short_pith_number":"pith:PSDR4ZBO","schema_version":"1.0","canonical_sha256":"7c871e642eed9dfb236fe404a977b902658ebd8776868f83640a4469a1192cd8","source":{"kind":"arxiv","id":"2508.03875","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Target Zone Blood Glucose Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, David H. Mguni, Jing Dong, Muhammad Salman Haleem, Wanrong Yang, Ziquan Liu","submitted_at":"2025-08-05T19:35:41Z","abstract_excerpt":"Managing physiological variables within clinically safe target zones is a central challenge in healthcare, particularly for chronic conditions such as Type 1 Diabetes Mellitus (T1DM). Reinforcement learning (RL) offers promise for personalising treatment, but struggles with the delayed and heterogeneous effects of interventions. We propose a novel RL framework to study and support decision-making in T1DM technologies, such as automated insulin delivery. Our approach captures the complex temporal dynamics of treatment by unifying two control modalities: \\textit{impulse control} for discrete, fa"},"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":"2508.03875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T19:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"b89c81be9fc5b3668b1d638e7ab30f4d21fe36d2456a4fa39a44babeb38f5b32","abstract_canon_sha256":"2b1a87458cd458073c51d4629048d93c0730eaae27b5e027cfb22f9d4fd4c618"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:16.644185Z","signature_b64":"vCiIBQmXWIPdzZqN0WQ/kcTVsOcuBAtZA4w8thPcJanstrh4YnNY1gVUH0itRWDODoQUIAwCWr4FRlRG/thJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c871e642eed9dfb236fe404a977b902658ebd8776868f83640a4469a1192cd8","last_reissued_at":"2026-07-05T11:49:16.643737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:16.643737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Target Zone Blood Glucose Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, David H. Mguni, Jing Dong, Muhammad Salman Haleem, Wanrong Yang, Ziquan Liu","submitted_at":"2025-08-05T19:35:41Z","abstract_excerpt":"Managing physiological variables within clinically safe target zones is a central challenge in healthcare, particularly for chronic conditions such as Type 1 Diabetes Mellitus (T1DM). Reinforcement learning (RL) offers promise for personalising treatment, but struggles with the delayed and heterogeneous effects of interventions. We propose a novel RL framework to study and support decision-making in T1DM technologies, such as automated insulin delivery. Our approach captures the complex temporal dynamics of treatment by unifying two control modalities: \\textit{impulse control} for discrete, fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03875","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/2508.03875/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":"2508.03875","created_at":"2026-07-05T11:49:16.643794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03875v1","created_at":"2026-07-05T11:49:16.643794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03875","created_at":"2026-07-05T11:49:16.643794+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSDR4ZBO5WO7","created_at":"2026-07-05T11:49:16.643794+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSDR4ZBO5WO7WI3P","created_at":"2026-07-05T11:49:16.643794+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSDR4ZBO","created_at":"2026-07-05T11:49:16.643794+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/PSDR4ZBO5WO7WI3P4QCKS55ZAJ","json":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ.json","graph_json":"https://pith.science/api/pith-number/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/graph.json","events_json":"https://pith.science/api/pith-number/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/events.json","paper":"https://pith.science/paper/PSDR4ZBO"},"agent_actions":{"view_html":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ","download_json":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ.json","view_paper":"https://pith.science/paper/PSDR4ZBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03875&json=true","fetch_graph":"https://pith.science/api/pith-number/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/action/storage_attestation","attest_author":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/action/author_attestation","sign_citation":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/action/citation_signature","submit_replication":"https://pith.science/pith/PSDR4ZBO5WO7WI3P4QCKS55ZAJ/action/replication_record"}},"created_at":"2026-07-05T11:49:16.643794+00:00","updated_at":"2026-07-05T11:49:16.643794+00:00"}