{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KPD5RQOB5HXPM3VN53ISJZ2XI","short_pith_number":"pith:6KPD5RQO","schema_version":"1.0","canonical_sha256":"f29e3ec60e0f4f77b3756f7689273aba09b1ecd1f406bdea7eb101f1283faeb9","source":{"kind":"arxiv","id":"2405.18610","version":1},"attestation_state":"computed","paper":{"title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fenglin Liu, Jiali Li, Jiandong Zhou, Mingcheng Zhu, Tingting Zhu, Yangchen Pan, Zhiyao Luo","submitted_at":"2024-05-28T21:40:00Z","abstract_excerpt":"Reinforcement learning (RL) has garnered increasing recognition for its potential to optimise dynamic treatment regimes (DTRs) in personalised medicine, particularly for drug dosage prescriptions and medication recommendations. However, a significant challenge persists: the absence of a unified framework for simulating diverse healthcare scenarios and a comprehensive analysis to benchmark the effectiveness of RL algorithms within these contexts. To address this gap, we introduce \\textit{DTR-Bench}, a benchmarking platform comprising four distinct simulation environments tailored to common DTR "},"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":"2405.18610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T21:40:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6ad34457276854bd0ec66c46fe6a1d4ddd6c9cf2383c97c0feff9a24fd0b3408","abstract_canon_sha256":"142140db72a5acbe771d17b21fe88fe504195a36b1009a410ce1bd93bba81fc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:28.008894Z","signature_b64":"MtOFlNmXy/O3vNt8OfRrY6x2MHeUh3ZFyEcLc1Vii+3+/Q94/3ZxbDdJdonEAUYXRw+kCgl8Kk5DnQvT3wD6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29e3ec60e0f4f77b3756f7689273aba09b1ecd1f406bdea7eb101f1283faeb9","last_reissued_at":"2026-07-05T08:24:28.008407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:28.008407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fenglin Liu, Jiali Li, Jiandong Zhou, Mingcheng Zhu, Tingting Zhu, Yangchen Pan, Zhiyao Luo","submitted_at":"2024-05-28T21:40:00Z","abstract_excerpt":"Reinforcement learning (RL) has garnered increasing recognition for its potential to optimise dynamic treatment regimes (DTRs) in personalised medicine, particularly for drug dosage prescriptions and medication recommendations. However, a significant challenge persists: the absence of a unified framework for simulating diverse healthcare scenarios and a comprehensive analysis to benchmark the effectiveness of RL algorithms within these contexts. To address this gap, we introduce \\textit{DTR-Bench}, a benchmarking platform comprising four distinct simulation environments tailored to common DTR "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18610","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/2405.18610/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":"2405.18610","created_at":"2026-07-05T08:24:28.008469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18610v1","created_at":"2026-07-05T08:24:28.008469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18610","created_at":"2026-07-05T08:24:28.008469+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KPD5RQOB5HX","created_at":"2026-07-05T08:24:28.008469+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KPD5RQOB5HXPM3V","created_at":"2026-07-05T08:24:28.008469+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KPD5RQO","created_at":"2026-07-05T08:24:28.008469+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/6KPD5RQOB5HXPM3VN53ISJZ2XI","json":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI.json","graph_json":"https://pith.science/api/pith-number/6KPD5RQOB5HXPM3VN53ISJZ2XI/graph.json","events_json":"https://pith.science/api/pith-number/6KPD5RQOB5HXPM3VN53ISJZ2XI/events.json","paper":"https://pith.science/paper/6KPD5RQO"},"agent_actions":{"view_html":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI","download_json":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI.json","view_paper":"https://pith.science/paper/6KPD5RQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18610&json=true","fetch_graph":"https://pith.science/api/pith-number/6KPD5RQOB5HXPM3VN53ISJZ2XI/graph.json","fetch_events":"https://pith.science/api/pith-number/6KPD5RQOB5HXPM3VN53ISJZ2XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI/action/storage_attestation","attest_author":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI/action/author_attestation","sign_citation":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI/action/citation_signature","submit_replication":"https://pith.science/pith/6KPD5RQOB5HXPM3VN53ISJZ2XI/action/replication_record"}},"created_at":"2026-07-05T08:24:28.008469+00:00","updated_at":"2026-07-05T08:24:28.008469+00:00"}