{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SOG4EKXGF5PC4WOXB7Y6PI7P6N","short_pith_number":"pith:SOG4EKXG","schema_version":"1.0","canonical_sha256":"938dc22ae62f5e2e59d70ff1e7a3eff357f4cd3425c478a75b6ae5b3416337dc","source":{"kind":"arxiv","id":"1908.08796","version":4},"attestation_state":"computed","paper":{"title":"Reinforcement Learning in Healthcare: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Jiming Liu, Shamim Nemati","submitted_at":"2019-08-22T08:32:49Z","abstract_excerpt":"As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisio"},"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":"1908.08796","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T08:32:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"591caadd3c60c85a37eb60d6826a12a78e75457f67a99143d087d2db605915cc","abstract_canon_sha256":"94c6936e632b85a7f8bc7993620d3423bfa239798e312e2aaaca94c266404c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:49.829557Z","signature_b64":"cqVgu/HZvxgdJDdNYn9z8xCVjM8k/XbZiD6nLoSnS0dooILSwHjnNXbm0T8HjJJFldIf/phefUHKQFHX6pNiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"938dc22ae62f5e2e59d70ff1e7a3eff357f4cd3425c478a75b6ae5b3416337dc","last_reissued_at":"2026-07-05T00:57:49.828996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:49.828996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Healthcare: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Jiming Liu, Shamim Nemati","submitted_at":"2019-08-22T08:32:49Z","abstract_excerpt":"As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised learning methods that usually rely on one-shot, exhaustive and supervised reward signals, RL tackles with sequential decision making problems with sampled, evaluative and delayed feedback simultaneously. Such distinctive features make RL technique a suitable candidate for developing powerful solutions in a variety of healthcare domains, where diagnosing decisio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08796","kind":"arxiv","version":4},"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/1908.08796/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":"1908.08796","created_at":"2026-07-05T00:57:49.829073+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08796v4","created_at":"2026-07-05T00:57:49.829073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08796","created_at":"2026-07-05T00:57:49.829073+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOG4EKXGF5PC","created_at":"2026-07-05T00:57:49.829073+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOG4EKXGF5PC4WOX","created_at":"2026-07-05T00:57:49.829073+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOG4EKXG","created_at":"2026-07-05T00:57:49.829073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2201.03544","citing_title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N","json":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N.json","graph_json":"https://pith.science/api/pith-number/SOG4EKXGF5PC4WOXB7Y6PI7P6N/graph.json","events_json":"https://pith.science/api/pith-number/SOG4EKXGF5PC4WOXB7Y6PI7P6N/events.json","paper":"https://pith.science/paper/SOG4EKXG"},"agent_actions":{"view_html":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N","download_json":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N.json","view_paper":"https://pith.science/paper/SOG4EKXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08796&json=true","fetch_graph":"https://pith.science/api/pith-number/SOG4EKXGF5PC4WOXB7Y6PI7P6N/graph.json","fetch_events":"https://pith.science/api/pith-number/SOG4EKXGF5PC4WOXB7Y6PI7P6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N/action/storage_attestation","attest_author":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N/action/author_attestation","sign_citation":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N/action/citation_signature","submit_replication":"https://pith.science/pith/SOG4EKXGF5PC4WOXB7Y6PI7P6N/action/replication_record"}},"created_at":"2026-07-05T00:57:49.829073+00:00","updated_at":"2026-07-05T00:57:49.829073+00:00"}