{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KPD5RQOB5HXPM3VN53ISJZ2XI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"142140db72a5acbe771d17b21fe88fe504195a36b1009a410ce1bd93bba81fc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T21:40:00Z","title_canon_sha256":"6ad34457276854bd0ec66c46fe6a1d4ddd6c9cf2383c97c0feff9a24fd0b3408"},"schema_version":"1.0","source":{"id":"2405.18610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18610","created_at":"2026-07-05T08:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18610v1","created_at":"2026-07-05T08:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18610","created_at":"2026-07-05T08:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"6KPD5RQOB5HX","created_at":"2026-07-05T08:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"6KPD5RQOB5HXPM3V","created_at":"2026-07-05T08:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"6KPD5RQO","created_at":"2026-07-05T08:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:5d3961bff1a085ebed0b8a3b1af062fd5674b209f781d1fb4b0aaf3f2d4dc100","target":"graph","created_at":"2026-07-05T08:24:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.18610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Fenglin Liu, Jiali Li, Jiandong Zhou, Mingcheng Zhu, Tingting Zhu, Yangchen Pan, Zhiyao Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T21:40:00Z","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18610","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:af3e756f105b0a6e46375495f4dd0af5fe65ddea26154612ad9905414174bd7a","target":"record","created_at":"2026-07-05T08:24:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"142140db72a5acbe771d17b21fe88fe504195a36b1009a410ce1bd93bba81fc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T21:40:00Z","title_canon_sha256":"6ad34457276854bd0ec66c46fe6a1d4ddd6c9cf2383c97c0feff9a24fd0b3408"},"schema_version":"1.0","source":{"id":"2405.18610","kind":"arxiv","version":1}},"canonical_sha256":"f29e3ec60e0f4f77b3756f7689273aba09b1ecd1f406bdea7eb101f1283faeb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f29e3ec60e0f4f77b3756f7689273aba09b1ecd1f406bdea7eb101f1283faeb9","first_computed_at":"2026-07-05T08:24:28.008407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:28.008407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MtOFlNmXy/O3vNt8OfRrY6x2MHeUh3ZFyEcLc1Vii+3+/Q94/3ZxbDdJdonEAUYXRw+kCgl8Kk5DnQvT3wD6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:28.008894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af3e756f105b0a6e46375495f4dd0af5fe65ddea26154612ad9905414174bd7a","sha256:5d3961bff1a085ebed0b8a3b1af062fd5674b209f781d1fb4b0aaf3f2d4dc100"],"state_sha256":"c05466fda4a59adba020343be5978137fab1ad1bf8e91c013bfed99fab3b037a"}