{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KRGA2HVNLI4R34SAHB4MOJA6MN","short_pith_number":"pith:KRGA2HVN","canonical_record":{"source":{"id":"1801.09271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-28T19:29:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"67063d5d5441831987a0ae3f3dd6b6d1154776e559bcba64052b88f3762f130a","abstract_canon_sha256":"9ae4ae3c39b4fc564797f1b4e714c28efb2ee08c21c6db0fff94762503180085"},"schema_version":"1.0"},"canonical_sha256":"544c0d1ead5a391df2403878c7241e637defb1eae9a7a25214522c8a2ad7238c","source":{"kind":"arxiv","id":"1801.09271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09271","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09271v1","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09271","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"KRGA2HVNLI4R","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KRGA2HVNLI4R34SA","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KRGA2HVN","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KRGA2HVNLI4R34SAHB4MOJA6MN","target":"record","payload":{"canonical_record":{"source":{"id":"1801.09271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-28T19:29:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"67063d5d5441831987a0ae3f3dd6b6d1154776e559bcba64052b88f3762f130a","abstract_canon_sha256":"9ae4ae3c39b4fc564797f1b4e714c28efb2ee08c21c6db0fff94762503180085"},"schema_version":"1.0"},"canonical_sha256":"544c0d1ead5a391df2403878c7241e637defb1eae9a7a25214522c8a2ad7238c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:57.984709Z","signature_b64":"89fnEgFwgOboYIpFBP/19KUACa1d2jmfj5Qt2qczKWTcqbPFb4HPryzqM2V9RKQjnPNV9rRUKJVGZBJqAZ9hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"544c0d1ead5a391df2403878c7241e637defb1eae9a7a25214522c8a2ad7238c","last_reissued_at":"2026-05-18T00:24:57.983935Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:57.983935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.09271","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J2fCsGY5nDUMnUxelZ7HNM/Fu6g/EBhMcKgZ5em6BoVZQAXvCsGLYYWokbOQIFjA7KccNDEsiSoivPJXj4gCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:34:38.471357Z"},"content_sha256":"382b987eecc83acdab770be786a9847a85a43436c28dab504cd2eed8a78bee1d","schema_version":"1.0","event_id":"sha256:382b987eecc83acdab770be786a9847a85a43436c28dab504cd2eed8a78bee1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KRGA2HVNLI4R34SAHB4MOJA6MN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Brent Logan, Jian Tang, Ning Liu, Yanzhi Wang, Ying Liu, Zhiyuan Xu","submitted_at":"2018-01-28T19:29:50Z","abstract_excerpt":"This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexity in heterogeneous disease progression and treatment choices, with the goal of providing doctor and patients the data-driven personalized decision recommendations. The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09271","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKcCnsoBHQxUgg31OYBC2aLgt+VAR3tQeEu/YaBHaBeuovFwgmbxcCHe5iyE0OLDjBiKMa5xzzgEw8geAWZbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:34:38.472030Z"},"content_sha256":"9fbaf17dae720eba1c737f4d5ad4bb324dd675090ea56301e16cc8a49d54c826","schema_version":"1.0","event_id":"sha256:9fbaf17dae720eba1c737f4d5ad4bb324dd675090ea56301e16cc8a49d54c826"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/bundle.json","state_url":"https://pith.science/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/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":"2026-06-07T06:34:38Z","links":{"resolver":"https://pith.science/pith/KRGA2HVNLI4R34SAHB4MOJA6MN","bundle":"https://pith.science/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/bundle.json","state":"https://pith.science/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KRGA2HVNLI4R34SAHB4MOJA6MN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KRGA2HVNLI4R34SAHB4MOJA6MN","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":"9ae4ae3c39b4fc564797f1b4e714c28efb2ee08c21c6db0fff94762503180085","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-28T19:29:50Z","title_canon_sha256":"67063d5d5441831987a0ae3f3dd6b6d1154776e559bcba64052b88f3762f130a"},"schema_version":"1.0","source":{"id":"1801.09271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.09271","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"1801.09271v1","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.09271","created_at":"2026-05-18T00:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"KRGA2HVNLI4R","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KRGA2HVNLI4R34SA","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KRGA2HVN","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:9fbaf17dae720eba1c737f4d5ad4bb324dd675090ea56301e16cc8a49d54c826","target":"graph","created_at":"2026-05-18T00:24:57Z","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"},"paper":{"abstract_excerpt":"This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexity in heterogeneous disease progression and treatment choices, with the goal of providing doctor and patients the data-driven personalized decision recommendations. The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and","authors_text":"Brent Logan, Jian Tang, Ning Liu, Yanzhi Wang, Ying Liu, Zhiyuan Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-28T19:29:50Z","title":"Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.09271","kind":"arxiv","version":1},"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":"sha256:382b987eecc83acdab770be786a9847a85a43436c28dab504cd2eed8a78bee1d","target":"record","created_at":"2026-05-18T00:24:57Z","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":"9ae4ae3c39b4fc564797f1b4e714c28efb2ee08c21c6db0fff94762503180085","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-28T19:29:50Z","title_canon_sha256":"67063d5d5441831987a0ae3f3dd6b6d1154776e559bcba64052b88f3762f130a"},"schema_version":"1.0","source":{"id":"1801.09271","kind":"arxiv","version":1}},"canonical_sha256":"544c0d1ead5a391df2403878c7241e637defb1eae9a7a25214522c8a2ad7238c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"544c0d1ead5a391df2403878c7241e637defb1eae9a7a25214522c8a2ad7238c","first_computed_at":"2026-05-18T00:24:57.983935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:57.983935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89fnEgFwgOboYIpFBP/19KUACa1d2jmfj5Qt2qczKWTcqbPFb4HPryzqM2V9RKQjnPNV9rRUKJVGZBJqAZ9hDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:57.984709Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.09271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:382b987eecc83acdab770be786a9847a85a43436c28dab504cd2eed8a78bee1d","sha256:9fbaf17dae720eba1c737f4d5ad4bb324dd675090ea56301e16cc8a49d54c826"],"state_sha256":"139eaf9d0be3d54a42c986b699e3d4fdda4d7450a4d9191cbe7746e1d894df7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqluwDGW2YcrdKavIuw//lJF1ckEHeQ7Q4pavIu8gKEYvIj3AtWHzzGNnXWBhADBIJGudty07GPGGINxdSEiAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:34:38.476399Z","bundle_sha256":"ce99987d14c21f020114ff62ce2110b9cbc5de5ce254c7866230cf3b075ab4d1"}}