{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QVHRYNGBJ2XUUVXNH2CNDI5DGP","short_pith_number":"pith:QVHRYNGB","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"},"canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","source":{"kind":"arxiv","id":"2410.07525","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07525","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07525v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07525","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"QVHRYNGBJ2XU","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"QVHRYNGBJ2XUUVXN","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"QVHRYNGB","created_at":"2026-07-05T09:20:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QVHRYNGBJ2XUUVXNH2CNDI5DGP","target":"record","payload":{"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"},"canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","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"},"source_kind":"arxiv","source_id":"2410.07525","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":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMNWzAryAWaPw8ghlOdbUAXSXMK5juX+zZQGTO5EiouC5qAtTafBPE3gJDrqcQxNFRIHZN5Eche23aPiqDqjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:47.097332Z"},"content_sha256":"5368adebe19d0824fd173f8df9c0723c6a80db02c676fe3d5e8f12e8f1070932","schema_version":"1.0","event_id":"sha256:5368adebe19d0824fd173f8df9c0723c6a80db02c676fe3d5e8f12e8f1070932"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QVHRYNGBJ2XUUVXNH2CNDI5DGP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VpdLmuZSKSDCfdN6Ptd/W0je+97Hezgs/r2v/4TRsaKmrVdFUYMvdPCduI+8TH1iqavTluyZm29wiwd9BjnCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:47.098164Z"},"content_sha256":"8c0923d94820fcb3f3dc2fb98a6bf02e3a2a4ef67c7f7cce5227645934779792","schema_version":"1.0","event_id":"sha256:8c0923d94820fcb3f3dc2fb98a6bf02e3a2a4ef67c7f7cce5227645934779792"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/bundle.json","state_url":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/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":"2026-08-09T04:57:47Z","links":{"resolver":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP","bundle":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/bundle.json","state":"https://pith.science/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVHRYNGBJ2XUUVXNH2CNDI5DGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QVHRYNGBJ2XUUVXNH2CNDI5DGP","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":"fbec9ca806c9863ff3e607060fe059bd865f79187bee93fdab92f407dda86d2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T01:36:27Z","title_canon_sha256":"5328df9da3a243490c99b284b0c5b6664205276bbe7897e8b1bf46926e1c0b52"},"schema_version":"1.0","source":{"id":"2410.07525","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07525","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07525v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07525","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"QVHRYNGBJ2XU","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"QVHRYNGBJ2XUUVXN","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"QVHRYNGB","created_at":"2026-07-05T09:20:04Z"}],"graph_snapshots":[{"event_id":"sha256:8c0923d94820fcb3f3dc2fb98a6bf02e3a2a4ef67c7f7cce5227645934779792","target":"graph","created_at":"2026-07-05T09:20:04Z","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/2410.07525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guiliang Liu, Nan Fang, Wei Gong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T01:36:27Z","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07525","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":"sha256:5368adebe19d0824fd173f8df9c0723c6a80db02c676fe3d5e8f12e8f1070932","target":"record","created_at":"2026-07-05T09:20:04Z","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":"fbec9ca806c9863ff3e607060fe059bd865f79187bee93fdab92f407dda86d2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T01:36:27Z","title_canon_sha256":"5328df9da3a243490c99b284b0c5b6664205276bbe7897e8b1bf46926e1c0b52"},"schema_version":"1.0","source":{"id":"2410.07525","kind":"arxiv","version":2}},"canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854f1c34c14eaf4a56ed3e84d1a3a333e57f146fe544161a52ab465645d54359","first_computed_at":"2026-07-05T09:20:04.546585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:04.546585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2RMgMws3pQrQ1n/wKbkGJDGQQeAiwOM/TcWpT4YViidYRTPXKZtuWLuQorCoLgsriEuIVvBdjRcU9Tyv3ewTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:04.546999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07525","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5368adebe19d0824fd173f8df9c0723c6a80db02c676fe3d5e8f12e8f1070932","sha256:8c0923d94820fcb3f3dc2fb98a6bf02e3a2a4ef67c7f7cce5227645934779792"],"state_sha256":"20503386c93e93142e6795b52680a721d2b4e3c1514a953f7020dea6835dfbf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYj+OYeoVsBwaHZJxO/Tsz7nSUSgF4NijtR73xnAPUUZCL/zrEP9hiXXRUoOQjMZXZUIgv8dCS2tuveaHFiPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:57:47.104421Z","bundle_sha256":"fcfed9ab9ebbc8a326f7c905365558004f30201d119e2264065c4276df578561"}}