{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CTCBT6UP5LGX2HBBIPRSDQ6YON","short_pith_number":"pith:CTCBT6UP","schema_version":"1.0","canonical_sha256":"14c419fa8feacd7d1c2143e321c3d87357e95ffacaf38beff92ebb1314eb26bd","source":{"kind":"arxiv","id":"1805.12298","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Reinforcement Learning Algorithms in Observational Health Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Christopher Mosch, David Sontag, David Wihl, Donghun Lee, Finale Doshi-Velez, Fredrik Johansson, Isaac Lage, Jack Dent, Jiayu Yao, Joshua Meier, Leo Anthony Celi, Linying Zhang, Li-wei H. Lehman, Matthieu Komorowski, Omer Gottesman, Srivatsan Srinivasan, Xuefeng Peng, Yi Ding","submitted_at":"2018-05-31T02:56:26Z","abstract_excerpt":"Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare. Reinforcement learning (RL) is a sub-field within machine learning that is concerned with learning how to make sequences of decisions so as to optimize long-term effects. Already, RL algorithms have been proposed to identify decision-making strategies for mechanical ventilation, sepsis management and treatment of schizophrenia. However, before implementing treatment policies learned by black-box algorithms in high-stakes clinical decision probl"},"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":"1805.12298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-31T02:56:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a75c8cbc19bcd5a9d4d14546e293e52161a25e0dfbf5ad1682a9569534b94902","abstract_canon_sha256":"7384936abd7397dfef53795c03b1836dac20d0b01fea070aeffef1ab3f8f0c9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:30.700808Z","signature_b64":"1TpiVzPzCNhgeH3/MiXf3CuCcb9tVNTpQonHLLR5nR9Q21RF7feK2rDvFXs+MEaVtQvTaB0aBWVnEfV9Ip7RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c419fa8feacd7d1c2143e321c3d87357e95ffacaf38beff92ebb1314eb26bd","last_reissued_at":"2026-05-18T00:14:30.700147Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:30.700147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Reinforcement Learning Algorithms in Observational Health Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Christopher Mosch, David Sontag, David Wihl, Donghun Lee, Finale Doshi-Velez, Fredrik Johansson, Isaac Lage, Jack Dent, Jiayu Yao, Joshua Meier, Leo Anthony Celi, Linying Zhang, Li-wei H. Lehman, Matthieu Komorowski, Omer Gottesman, Srivatsan Srinivasan, Xuefeng Peng, Yi Ding","submitted_at":"2018-05-31T02:56:26Z","abstract_excerpt":"Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare. Reinforcement learning (RL) is a sub-field within machine learning that is concerned with learning how to make sequences of decisions so as to optimize long-term effects. Already, RL algorithms have been proposed to identify decision-making strategies for mechanical ventilation, sepsis management and treatment of schizophrenia. However, before implementing treatment policies learned by black-box algorithms in high-stakes clinical decision probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12298","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":""},"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":"1805.12298","created_at":"2026-05-18T00:14:30.700240+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.12298v1","created_at":"2026-05-18T00:14:30.700240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12298","created_at":"2026-05-18T00:14:30.700240+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTCBT6UP5LGX","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTCBT6UP5LGX2HBB","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTCBT6UP","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.23040","citing_title":"Treatment, evidence, imitation, and chat","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13054","citing_title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":214,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON","json":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON.json","graph_json":"https://pith.science/api/pith-number/CTCBT6UP5LGX2HBBIPRSDQ6YON/graph.json","events_json":"https://pith.science/api/pith-number/CTCBT6UP5LGX2HBBIPRSDQ6YON/events.json","paper":"https://pith.science/paper/CTCBT6UP"},"agent_actions":{"view_html":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON","download_json":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON.json","view_paper":"https://pith.science/paper/CTCBT6UP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.12298&json=true","fetch_graph":"https://pith.science/api/pith-number/CTCBT6UP5LGX2HBBIPRSDQ6YON/graph.json","fetch_events":"https://pith.science/api/pith-number/CTCBT6UP5LGX2HBBIPRSDQ6YON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON/action/storage_attestation","attest_author":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON/action/author_attestation","sign_citation":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON/action/citation_signature","submit_replication":"https://pith.science/pith/CTCBT6UP5LGX2HBBIPRSDQ6YON/action/replication_record"}},"created_at":"2026-05-18T00:14:30.700240+00:00","updated_at":"2026-05-18T00:14:30.700240+00:00"}