{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ACBHHKFSJ4KI27AUXFUREIZGD4","short_pith_number":"pith:ACBHHKFS","canonical_record":{"source":{"id":"2302.10261","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T19:47:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"990467571ef09f4328341b6069bf9565012c7c177ba7e843bf9a9e759a694e58","abstract_canon_sha256":"f67231a1aa7368f7fb490713a30aec2387db41aed6f39baa335f8760a684fcef"},"schema_version":"1.0"},"canonical_sha256":"008273a8b24f148d7c14b9691223261f0be6967606dc07f8be60fa15f64c692b","source":{"kind":"arxiv","id":"2302.10261","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ACBHHKFSJ4KI27AUXFUREIZGD4","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10261","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T19:47:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"990467571ef09f4328341b6069bf9565012c7c177ba7e843bf9a9e759a694e58","abstract_canon_sha256":"f67231a1aa7368f7fb490713a30aec2387db41aed6f39baa335f8760a684fcef"},"schema_version":"1.0"},"canonical_sha256":"008273a8b24f148d7c14b9691223261f0be6967606dc07f8be60fa15f64c692b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:38.546087Z","signature_b64":"CeuKQzQhh8BVpoHEYPq3r6ozCIRgdZO6lD6MG5j5jpD7KUkQEZvgiAvilYkGTc+7/G6hUcQ3CJb1j2U6dhNLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"008273a8b24f148d7c14b9691223261f0be6967606dc07f8be60fa15f64c692b","last_reissued_at":"2026-07-05T05:46:38.545607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:38.545607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10261","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5SvItKtA9xqvXOojGV1eBJJPcGFlJkF/rnfqIrLP0OhRtM2uWAG4nwJYIdn/0xmxZDQPC+SnKyuHi8XOL+vBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:58:04.863614Z"},"content_sha256":"a69666dfea882512f5acbb51355d3058d62d45099b2b38eccefaee1e7f2c3f3f","schema_version":"1.0","event_id":"sha256:a69666dfea882512f5acbb51355d3058d62d45099b2b38eccefaee1e7f2c3f3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ACBHHKFSJ4KI27AUXFUREIZGD4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Cost-Effective Medical Diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joseph Kim, Kaixuan Huang, Mengdi Wang, Yikuan Li, Yuan Luo, Zheng Yu","submitted_at":"2023-02-20T19:47:25Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10261","kind":"arxiv","version":2},"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/2302.10261/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:46:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yLGYqNbf+sy5X0Ht+irWU6A+XtMHakfbFluTuSPS8q9sp4byIuTm/LpCH+N/lb0O5Fj2Ru2MXIOHfLvUFzBCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:58:04.864223Z"},"content_sha256":"b87919fb518ea036653da5c9159bd9bf4eae51288ecc8ab093b44a8dc4459504","schema_version":"1.0","event_id":"sha256:b87919fb518ea036653da5c9159bd9bf4eae51288ecc8ab093b44a8dc4459504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/bundle.json","state_url":"https://pith.science/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:58:04Z","links":{"resolver":"https://pith.science/pith/ACBHHKFSJ4KI27AUXFUREIZGD4","bundle":"https://pith.science/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/bundle.json","state":"https://pith.science/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACBHHKFSJ4KI27AUXFUREIZGD4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAcuxgdRws2i1S93v84ZUpdJFGSy73bgynbnrLGaKIM5JJnxVbg4VP9iRCn/+td/A67uPwt+um2f5p9phJ+6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:58:04.869570Z","bundle_sha256":"74ccba077119427d0c98ddad973eca51156c39f86b97343f37bb4e321808c580"}}