{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ACBHHKFSJ4KI27AUXFUREIZGD4","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":"f67231a1aa7368f7fb490713a30aec2387db41aed6f39baa335f8760a684fcef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T19:47:25Z","title_canon_sha256":"990467571ef09f4328341b6069bf9565012c7c177ba7e843bf9a9e759a694e58"},"schema_version":"1.0","source":{"id":"2302.10261","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10261","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10261v2","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10261","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"ACBHHKFSJ4KI","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"ACBHHKFSJ4KI27AU","created_at":"2026-07-05T05:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"ACBHHKFS","created_at":"2026-07-05T05:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:b87919fb518ea036653da5c9159bd9bf4eae51288ecc8ab093b44a8dc4459504","target":"graph","created_at":"2026-07-05T05:46:38Z","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/2302.10261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamic diagnosis is desirable when medical tests are costly or time-consuming. In this work, we use reinforcement learning (RL) to find a dynamic policy that selects lab test panels sequentially based on previous observations, ensuring accurate testing at a low cost. Clinical diagnostic data are often highly imbalanced; therefore, we aim to maximize the $F_1$ score instead of the error rate. However, optimizing the non-concave $F_1$ score is not a classic RL problem, thus invalidates standard RL methods. To remedy this issue, we develop a reward shaping approach, leveraging properties of the ","authors_text":"Joseph Kim, Kaixuan Huang, Mengdi Wang, Yikuan Li, Yuan Luo, Zheng Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T19:47:25Z","title":"Deep Reinforcement Learning for Cost-Effective Medical Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10261","kind":"arxiv","version":2},"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:a69666dfea882512f5acbb51355d3058d62d45099b2b38eccefaee1e7f2c3f3f","target":"record","created_at":"2026-07-05T05:46:38Z","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":"f67231a1aa7368f7fb490713a30aec2387db41aed6f39baa335f8760a684fcef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T19:47:25Z","title_canon_sha256":"990467571ef09f4328341b6069bf9565012c7c177ba7e843bf9a9e759a694e58"},"schema_version":"1.0","source":{"id":"2302.10261","kind":"arxiv","version":2}},"canonical_sha256":"008273a8b24f148d7c14b9691223261f0be6967606dc07f8be60fa15f64c692b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"008273a8b24f148d7c14b9691223261f0be6967606dc07f8be60fa15f64c692b","first_computed_at":"2026-07-05T05:46:38.545607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:38.545607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CeuKQzQhh8BVpoHEYPq3r6ozCIRgdZO6lD6MG5j5jpD7KUkQEZvgiAvilYkGTc+7/G6hUcQ3CJb1j2U6dhNLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:38.546087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10261","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a69666dfea882512f5acbb51355d3058d62d45099b2b38eccefaee1e7f2c3f3f","sha256:b87919fb518ea036653da5c9159bd9bf4eae51288ecc8ab093b44a8dc4459504"],"state_sha256":"1dfcf23bdca52869e6a9546364d3169b7e1a4fa865bdd77f08583b0a95296f24"}