{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QVHRYNGBJ2XUUVXNH2CNDI5DGP","short_pith_number":"pith:QVHRYNGB","schema_version":"1.0","canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","source":{"kind":"arxiv","id":"2410.07525","version":2},"attestation_state":"computed","paper":{"title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guiliang Liu, Nan Fang, Wei Gong","submitted_at":"2024-10-10T01:36:27Z","abstract_excerpt":"Reinforcement Learning (RL) applied in healthcare can lead to unsafe medical decisions and treatment, such as excessive dosages or abrupt changes, often due to agents overlooking common-sense constraints. Consequently, Constrained Reinforcement Learning (CRL) is a natural choice for safe decisions. However, specifying the exact cost function is inherently difficult in healthcare. Recent Inverse Constrained Reinforcement Learning (ICRL) is a promising approach that infers constraints from expert demonstrations. ICRL algorithms model Markovian decisions in an interactive environment. These setti"},"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":"2410.07525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T01:36:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5328df9da3a243490c99b284b0c5b6664205276bbe7897e8b1bf46926e1c0b52","abstract_canon_sha256":"fbec9ca806c9863ff3e607060fe059bd865f79187bee93fdab92f407dda86d2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:04.546999Z","signature_b64":"2RMgMws3pQrQ1n/wKbkGJDGQQeAiwOM/TcWpT4YViidYRTPXKZtuWLuQorCoLgsriEuIVvBdjRcU9Tyv3ewTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","last_reissued_at":"2026-07-05T09:20:04.546585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:04.546585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guiliang Liu, Nan Fang, Wei Gong","submitted_at":"2024-10-10T01:36:27Z","abstract_excerpt":"Reinforcement Learning (RL) applied in healthcare can lead to unsafe medical decisions and treatment, such as excessive dosages or abrupt changes, often due to agents overlooking common-sense constraints. Consequently, Constrained Reinforcement Learning (CRL) is a natural choice for safe decisions. However, specifying the exact cost function is inherently difficult in healthcare. Recent Inverse Constrained Reinforcement Learning (ICRL) is a promising approach that infers constraints from expert demonstrations. ICRL algorithms model Markovian decisions in an interactive environment. These setti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07525","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/2410.07525/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":"2410.07525","created_at":"2026-07-05T09:20:04.546643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07525v2","created_at":"2026-07-05T09:20:04.546643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07525","created_at":"2026-07-05T09:20:04.546643+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVHRYNGBJ2XU","created_at":"2026-07-05T09:20:04.546643+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVHRYNGBJ2XUUVXN","created_at":"2026-07-05T09:20:04.546643+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVHRYNGB","created_at":"2026-07-05T09:20:04.546643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07681","citing_title":"MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP","json":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP.json","graph_json":"https://pith.science/api/pith-number/QVHRYNGBJ2XUUVXNH2CNDI5DGP/graph.json","events_json":"https://pith.science/api/pith-number/QVHRYNGBJ2XUUVXNH2CNDI5DGP/events.json","paper":"https://pith.science/paper/QVHRYNGB"},"agent_actions":{"view_html":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP","download_json":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP.json","view_paper":"https://pith.science/paper/QVHRYNGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07525&json=true","fetch_graph":"https://pith.science/api/pith-number/QVHRYNGBJ2XUUVXNH2CNDI5DGP/graph.json","fetch_events":"https://pith.science/api/pith-number/QVHRYNGBJ2XUUVXNH2CNDI5DGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/action/storage_attestation","attest_author":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/action/author_attestation","sign_citation":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/action/citation_signature","submit_replication":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/action/replication_record"}},"created_at":"2026-07-05T09:20:04.546643+00:00","updated_at":"2026-07-05T09:20:04.546643+00:00"}