{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DPSUTSYCKI2DCOJKDDHR2W2GI3","short_pith_number":"pith:DPSUTSYC","schema_version":"1.0","canonical_sha256":"1be549cb02523431392a18cf1d5b4646ce4c93783c9d0ee322c6c575ed98b656","source":{"kind":"arxiv","id":"2606.01028","version":1},"attestation_state":"computed","paper":{"title":"MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Katsuki Fujisawa, Ken Kawano, Kyoung-Sook Kim, Mehrshad Sadria, Richard Weiss, Sebastien Gros, Xiao Hu, Xin Liu, Xun Shen, Ying Chen, Yongqi Zhou, Yoshihiko Fujisawa, Yuepeng Wang","submitted_at":"2026-05-31T05:36:03Z","abstract_excerpt":"Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals. Existing RL formulations and simulated environments, however, are based on discrete-time MDP or POMDP abstractions with fixed or pre-specified decision intervals. Thus, it remains difficult to evaluate whether RL methods can handle time-interval-dependent disease progression, personalized treatment response, and safety between cons"},"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":"2606.01028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T05:36:03Z","cross_cats_sorted":[],"title_canon_sha256":"3aa46efbad344a31231d730c31d55c650a8c2f2b1372dbd8085d62b19833b0d8","abstract_canon_sha256":"d25968d178aef48beecc9386d80026f46bb1af6e047e148a7ee76659d3bc9d28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:18.973718Z","signature_b64":"FgTH7huJ+aKaVlKNgEbHO2F+BENjILtt227E7lLxtJ/LBD6HxuKZyT4EfxyFq8/YP3eJF7WW0RZJbjYZw6osDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be549cb02523431392a18cf1d5b4646ce4c93783c9d0ee322c6c575ed98b656","last_reissued_at":"2026-06-02T01:04:18.973271Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:18.973271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Katsuki Fujisawa, Ken Kawano, Kyoung-Sook Kim, Mehrshad Sadria, Richard Weiss, Sebastien Gros, Xiao Hu, Xin Liu, Xun Shen, Ying Chen, Yongqi Zhou, Yoshihiko Fujisawa, Yuepeng Wang","submitted_at":"2026-05-31T05:36:03Z","abstract_excerpt":"Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals. Existing RL formulations and simulated environments, however, are based on discrete-time MDP or POMDP abstractions with fixed or pre-specified decision intervals. Thus, it remains difficult to evaluate whether RL methods can handle time-interval-dependent disease progression, personalized treatment response, and safety between cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01028","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/2606.01028/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":"2606.01028","created_at":"2026-06-02T01:04:18.973341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01028v1","created_at":"2026-06-02T01:04:18.973341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01028","created_at":"2026-06-02T01:04:18.973341+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPSUTSYCKI2D","created_at":"2026-06-02T01:04:18.973341+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPSUTSYCKI2DCOJK","created_at":"2026-06-02T01:04:18.973341+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPSUTSYC","created_at":"2026-06-02T01:04:18.973341+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/DPSUTSYCKI2DCOJKDDHR2W2GI3","json":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3.json","graph_json":"https://pith.science/api/pith-number/DPSUTSYCKI2DCOJKDDHR2W2GI3/graph.json","events_json":"https://pith.science/api/pith-number/DPSUTSYCKI2DCOJKDDHR2W2GI3/events.json","paper":"https://pith.science/paper/DPSUTSYC"},"agent_actions":{"view_html":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3","download_json":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3.json","view_paper":"https://pith.science/paper/DPSUTSYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01028&json=true","fetch_graph":"https://pith.science/api/pith-number/DPSUTSYCKI2DCOJKDDHR2W2GI3/graph.json","fetch_events":"https://pith.science/api/pith-number/DPSUTSYCKI2DCOJKDDHR2W2GI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3/action/storage_attestation","attest_author":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3/action/author_attestation","sign_citation":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3/action/citation_signature","submit_replication":"https://pith.science/pith/DPSUTSYCKI2DCOJKDDHR2W2GI3/action/replication_record"}},"created_at":"2026-06-02T01:04:18.973341+00:00","updated_at":"2026-06-02T01:04:18.973341+00:00"}