{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HI55E2MGP2PLVQG3EEGJFLRJDO","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":"7639a8970be6d74dec1ad323a0a31090767138864cbc62f409636d4ce68efe32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-02T03:16:59Z","title_canon_sha256":"c8c927cf87871cb5c33adb5fc3143ac0f1cd04e1b8f36dd4c23d3091190308c9"},"schema_version":"1.0","source":{"id":"2301.00512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.00512","created_at":"2026-07-05T05:29:47Z"},{"alias_kind":"arxiv_version","alias_value":"2301.00512v1","created_at":"2026-07-05T05:29:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00512","created_at":"2026-07-05T05:29:47Z"},{"alias_kind":"pith_short_12","alias_value":"HI55E2MGP2PL","created_at":"2026-07-05T05:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"HI55E2MGP2PLVQG3","created_at":"2026-07-05T05:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"HI55E2MG","created_at":"2026-07-05T05:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:f4576665504ae0077fa3c1608ff03cc1fff9716408dfe299e728f08285a2ac56","target":"graph","created_at":"2026-07-05T05:29:47Z","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/2301.00512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Drug dosing is an important application of AI, which can be formulated as a Reinforcement Learning (RL) problem. In this paper, we identify two major challenges of using RL for drug dosing: delayed and prolonged effects of administering medications, which break the Markov assumption of the RL framework. We focus on prolongedness and define PAE-POMDP (Prolonged Action Effect-Partially Observable Markov Decision Process), a subclass of POMDPs in which the Markov assumption does not hold specifically due to prolonged effects of actions. Motivated by the pharmacology literature, we propose a simpl","authors_text":"Adriana Romero-Soriano, Doina Precup, Marc-Andr\\'e Legault, Sumana Basu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-02T03:16:59Z","title":"On the Challenges of using Reinforcement Learning in Precision Drug Dosing: Delay and Prolongedness of Action Effects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00512","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":"sha256:2e3f1453d353b10a1feca207dfb3dfb11119f569e6019ecb9eeb46b510ac2625","target":"record","created_at":"2026-07-05T05:29:47Z","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":"7639a8970be6d74dec1ad323a0a31090767138864cbc62f409636d4ce68efe32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-02T03:16:59Z","title_canon_sha256":"c8c927cf87871cb5c33adb5fc3143ac0f1cd04e1b8f36dd4c23d3091190308c9"},"schema_version":"1.0","source":{"id":"2301.00512","kind":"arxiv","version":1}},"canonical_sha256":"3a3bd269867e9ebac0db210c92ae291baca092bebc87d7977b1a519ffc9166d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a3bd269867e9ebac0db210c92ae291baca092bebc87d7977b1a519ffc9166d5","first_computed_at":"2026-07-05T05:29:47.119719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:47.119719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L3yr26sGU5QutNL+OKu9BhsNQOFLOkXPwdKJWBK73OIKPmP1gCMKBijZbmxaLLjY+Tz8Z0/F0Dp3krpkwXwSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:47.120146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.00512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3f1453d353b10a1feca207dfb3dfb11119f569e6019ecb9eeb46b510ac2625","sha256:f4576665504ae0077fa3c1608ff03cc1fff9716408dfe299e728f08285a2ac56"],"state_sha256":"574b20cf813091f58298e8b8900e3b1baf008a5bdbcaf178db1ff7de63b16426"}