{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GKOF2NHE6KUC7VUTB5XFDNJSMA","short_pith_number":"pith:GKOF2NHE","schema_version":"1.0","canonical_sha256":"329c5d34e4f2a82fd6930f6e51b5326015c1a42049eab91020e81a9aaf9654bd","source":{"kind":"arxiv","id":"2203.02605","version":3},"attestation_state":"computed","paper":{"title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ME"],"primary_cat":"stat.ML","authors_text":"Bibhas Chakraborty, Joseph Jay Williams, Nina Deliu","submitted_at":"2022-03-04T23:14:02Z","abstract_excerpt":"In recent years, reinforcement learning (RL) has acquired a prominent position in health-related sequential decision-making problems, gaining traction as a valuable tool for delivering adaptive interventions (AIs). However, in part due to a poor synergy between the methodological and the applied communities, its real-life application is still limited and its potential is still to be realized. To address this gap, our work provides the first unified technical survey on RL methods, complemented with case studies, for constructing various types of AIs in healthcare. In particular, using the commo"},"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":"2203.02605","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2022-03-04T23:14:02Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ME"],"title_canon_sha256":"18459c40c430db54f3cef4dc5b116b62d8a53ab9714a3146c67fe0fa2b53ad60","abstract_canon_sha256":"99027aada4009b69ef6592b4a88af6ff098a2ad8124765187b826f6f3a96d763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:20.401453Z","signature_b64":"wPMh7Bit2obJBPh67eeAE24JZk3aHQnd0vma9owEGvyH/foqAnePD3JxOlTW67z9aC3VDSFmiPq70HQ+zyAXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"329c5d34e4f2a82fd6930f6e51b5326015c1a42049eab91020e81a9aaf9654bd","last_reissued_at":"2026-07-05T08:43:20.400939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:20.400939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ME"],"primary_cat":"stat.ML","authors_text":"Bibhas Chakraborty, Joseph Jay Williams, Nina Deliu","submitted_at":"2022-03-04T23:14:02Z","abstract_excerpt":"In recent years, reinforcement learning (RL) has acquired a prominent position in health-related sequential decision-making problems, gaining traction as a valuable tool for delivering adaptive interventions (AIs). However, in part due to a poor synergy between the methodological and the applied communities, its real-life application is still limited and its potential is still to be realized. To address this gap, our work provides the first unified technical survey on RL methods, complemented with case studies, for constructing various types of AIs in healthcare. In particular, using the commo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02605","kind":"arxiv","version":3},"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/2203.02605/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":"2203.02605","created_at":"2026-07-05T08:43:20.401016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02605v3","created_at":"2026-07-05T08:43:20.401016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02605","created_at":"2026-07-05T08:43:20.401016+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKOF2NHE6KUC","created_at":"2026-07-05T08:43:20.401016+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKOF2NHE6KUC7VUT","created_at":"2026-07-05T08:43:20.401016+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKOF2NHE","created_at":"2026-07-05T08:43:20.401016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17285","citing_title":"On Fisher Consistency of Surrogate Losses for Optimal Dynamic Treatment Regimes with Multiple Categorical Treatments per Stage","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA","json":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA.json","graph_json":"https://pith.science/api/pith-number/GKOF2NHE6KUC7VUTB5XFDNJSMA/graph.json","events_json":"https://pith.science/api/pith-number/GKOF2NHE6KUC7VUTB5XFDNJSMA/events.json","paper":"https://pith.science/paper/GKOF2NHE"},"agent_actions":{"view_html":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA","download_json":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA.json","view_paper":"https://pith.science/paper/GKOF2NHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02605&json=true","fetch_graph":"https://pith.science/api/pith-number/GKOF2NHE6KUC7VUTB5XFDNJSMA/graph.json","fetch_events":"https://pith.science/api/pith-number/GKOF2NHE6KUC7VUTB5XFDNJSMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA/action/storage_attestation","attest_author":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA/action/author_attestation","sign_citation":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA/action/citation_signature","submit_replication":"https://pith.science/pith/GKOF2NHE6KUC7VUTB5XFDNJSMA/action/replication_record"}},"created_at":"2026-07-05T08:43:20.401016+00:00","updated_at":"2026-07-05T08:43:20.401016+00:00"}