{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F22A4W7LGHU6CITUKYXD7OT34T","short_pith_number":"pith:F22A4W7L","schema_version":"1.0","canonical_sha256":"2eb40e5beb31e9e12274562e3fba7be4d5cb8908fe512b1abb773fb7f7fa9976","source":{"kind":"arxiv","id":"1711.09602","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Sepsis Treatment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aniruddh Raghu, Imran Ahmed, Leo Celi, Marzyeh Ghassemi, Matthieu Komorowski, Peter Szolovits","submitted_at":"2017-11-27T09:49:57Z","abstract_excerpt":"Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we propose an approach to deduce treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Our model learns clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. The learned policie"},"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":"1711.09602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-27T09:49:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb64d44e7b85b8832724c7a0105d8785dab7842f601631755ea01b04b7c76c83","abstract_canon_sha256":"b47eeaafe8d2f03b6d144a6ec6694bb5cc7d60c2d484149c042455986bc12d8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:35.026186Z","signature_b64":"PAsPNZZjBASK+TvwYjEMb9t3noPkrREsvmhotyulZkSFD5lI8aVPlaFdJzHIGCitaSAdyFuD5vdWWbhBHp2iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eb40e5beb31e9e12274562e3fba7be4d5cb8908fe512b1abb773fb7f7fa9976","last_reissued_at":"2026-05-18T00:29:35.025544Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:35.025544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Sepsis Treatment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aniruddh Raghu, Imran Ahmed, Leo Celi, Marzyeh Ghassemi, Matthieu Komorowski, Peter Szolovits","submitted_at":"2017-11-27T09:49:57Z","abstract_excerpt":"Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we propose an approach to deduce treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Our model learns clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. The learned policie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09602","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.09602","created_at":"2026-05-18T00:29:35.025642+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09602v1","created_at":"2026-05-18T00:29:35.025642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09602","created_at":"2026-05-18T00:29:35.025642+00:00"},{"alias_kind":"pith_short_12","alias_value":"F22A4W7LGHU6","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"F22A4W7LGHU6CITU","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"F22A4W7L","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2601.23154","citing_title":"On Safer Reinforcement Learning for Sedation and Analgesia in Intensive Care","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2506.23040","citing_title":"Treatment, evidence, imitation, and chat","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02112","citing_title":"An adaptive variance estimator for relative sparsity","ref_index":203,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T","json":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T.json","graph_json":"https://pith.science/api/pith-number/F22A4W7LGHU6CITUKYXD7OT34T/graph.json","events_json":"https://pith.science/api/pith-number/F22A4W7LGHU6CITUKYXD7OT34T/events.json","paper":"https://pith.science/paper/F22A4W7L"},"agent_actions":{"view_html":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T","download_json":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T.json","view_paper":"https://pith.science/paper/F22A4W7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09602&json=true","fetch_graph":"https://pith.science/api/pith-number/F22A4W7LGHU6CITUKYXD7OT34T/graph.json","fetch_events":"https://pith.science/api/pith-number/F22A4W7LGHU6CITUKYXD7OT34T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T/action/storage_attestation","attest_author":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T/action/author_attestation","sign_citation":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T/action/citation_signature","submit_replication":"https://pith.science/pith/F22A4W7LGHU6CITUKYXD7OT34T/action/replication_record"}},"created_at":"2026-05-18T00:29:35.025642+00:00","updated_at":"2026-05-18T00:29:35.025642+00:00"}