{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4YKPLIXTPMXH7BUUX3OURCLGIR","short_pith_number":"pith:4YKPLIXT","canonical_record":{"source":{"id":"2301.05664","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T17:01:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a57f3e37e0a2ddab5aa1922a5b6f4b85efc8eea063c749a9d2b3e6fde443bfc5","abstract_canon_sha256":"98839a7d5cc42643d675009df1c8335b324a2d2f3e98cbd87634c230fd7f59f2"},"schema_version":"1.0"},"canonical_sha256":"e614f5a2f37b2e7f8694bedd488966444ec98301f76b1c8ae72b9d63e1e3964a","source":{"kind":"arxiv","id":"2301.05664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05664","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05664v2","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05664","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"4YKPLIXTPMXH","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"4YKPLIXTPMXH7BUU","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"4YKPLIXT","created_at":"2026-07-05T05:36:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4YKPLIXTPMXH7BUUX3OURCLGIR","target":"record","payload":{"canonical_record":{"source":{"id":"2301.05664","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T17:01:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a57f3e37e0a2ddab5aa1922a5b6f4b85efc8eea063c749a9d2b3e6fde443bfc5","abstract_canon_sha256":"98839a7d5cc42643d675009df1c8335b324a2d2f3e98cbd87634c230fd7f59f2"},"schema_version":"1.0"},"canonical_sha256":"e614f5a2f37b2e7f8694bedd488966444ec98301f76b1c8ae72b9d63e1e3964a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:52.403522Z","signature_b64":"ByaWY1guSMw0ctFU7satg4paD8nKOWWpotzfQ1U+KD/myDMlFPMNV+8CzZt6UVFj3XyhCbToXFGLa00FU6c8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e614f5a2f37b2e7f8694bedd488966444ec98301f76b1c8ae72b9d63e1e3964a","last_reissued_at":"2026-07-05T05:36:52.403075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:52.403075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.05664","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":"2026-07-05T05:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oDv6iRIoY5Y0aFwO0TArc4iGya3hqE6sLh93jJM7BB5yTdOsl97FsNZ2bf8XTUa0YGKm3azo7lg6V8zX3l4gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:28:07.378055Z"},"content_sha256":"8730bdfc5979338668badbea5aa8915b947235ebccad69ee1d828edee4e74aa6","schema_version":"1.0","event_id":"sha256:8730bdfc5979338668badbea5aa8915b947235ebccad69ee1d828edee4e74aa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4YKPLIXTPMXH7BUUX3OURCLGIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marzyeh Ghassemi, Sonali Parbhoo, Taylor W. Killian","submitted_at":"2023-01-13T17:01:58Z","abstract_excerpt":"In safety-critical decision-making scenarios being able to identify worst-case outcomes, or dead-ends is crucial in order to develop safe and reliable policies in practice. These situations are typically rife with uncertainty due to unknown or stochastic characteristics of the environment as well as limited offline training data. As a result, the value of a decision at any time point should be based on the distribution of its anticipated effects. We propose a framework to identify worst-case decision points, by explicitly estimating distributions of the expected return of a decision. These est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05664","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/2301.05664/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":"2026-07-05T05:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnzK8FqHjGX+W9zPrVam/tmanxA4T/RkTn/W93wcSLdrPHkFYMk2PTbCbyqtSwdTG+y5p4y5YPIiMOyMCy+XAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:28:07.378576Z"},"content_sha256":"fec71bf07499c06e7798a007723cbfb019e9241249f974db3474520336dc8d41","schema_version":"1.0","event_id":"sha256:fec71bf07499c06e7798a007723cbfb019e9241249f974db3474520336dc8d41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/bundle.json","state_url":"https://pith.science/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/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":"2026-08-07T23:28:07Z","links":{"resolver":"https://pith.science/pith/4YKPLIXTPMXH7BUUX3OURCLGIR","bundle":"https://pith.science/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/bundle.json","state":"https://pith.science/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YKPLIXTPMXH7BUUX3OURCLGIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4YKPLIXTPMXH7BUUX3OURCLGIR","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":"98839a7d5cc42643d675009df1c8335b324a2d2f3e98cbd87634c230fd7f59f2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T17:01:58Z","title_canon_sha256":"a57f3e37e0a2ddab5aa1922a5b6f4b85efc8eea063c749a9d2b3e6fde443bfc5"},"schema_version":"1.0","source":{"id":"2301.05664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05664","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05664v2","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05664","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"4YKPLIXTPMXH","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"4YKPLIXTPMXH7BUU","created_at":"2026-07-05T05:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"4YKPLIXT","created_at":"2026-07-05T05:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:fec71bf07499c06e7798a007723cbfb019e9241249f974db3474520336dc8d41","target":"graph","created_at":"2026-07-05T05:36:52Z","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/2301.05664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In safety-critical decision-making scenarios being able to identify worst-case outcomes, or dead-ends is crucial in order to develop safe and reliable policies in practice. These situations are typically rife with uncertainty due to unknown or stochastic characteristics of the environment as well as limited offline training data. As a result, the value of a decision at any time point should be based on the distribution of its anticipated effects. We propose a framework to identify worst-case decision points, by explicitly estimating distributions of the expected return of a decision. These est","authors_text":"Marzyeh Ghassemi, Sonali Parbhoo, Taylor W. Killian","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T17:01:58Z","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05664","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":"sha256:8730bdfc5979338668badbea5aa8915b947235ebccad69ee1d828edee4e74aa6","target":"record","created_at":"2026-07-05T05:36:52Z","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":"98839a7d5cc42643d675009df1c8335b324a2d2f3e98cbd87634c230fd7f59f2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-13T17:01:58Z","title_canon_sha256":"a57f3e37e0a2ddab5aa1922a5b6f4b85efc8eea063c749a9d2b3e6fde443bfc5"},"schema_version":"1.0","source":{"id":"2301.05664","kind":"arxiv","version":2}},"canonical_sha256":"e614f5a2f37b2e7f8694bedd488966444ec98301f76b1c8ae72b9d63e1e3964a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e614f5a2f37b2e7f8694bedd488966444ec98301f76b1c8ae72b9d63e1e3964a","first_computed_at":"2026-07-05T05:36:52.403075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:52.403075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ByaWY1guSMw0ctFU7satg4paD8nKOWWpotzfQ1U+KD/myDMlFPMNV+8CzZt6UVFj3XyhCbToXFGLa00FU6c8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:52.403522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.05664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8730bdfc5979338668badbea5aa8915b947235ebccad69ee1d828edee4e74aa6","sha256:fec71bf07499c06e7798a007723cbfb019e9241249f974db3474520336dc8d41"],"state_sha256":"b18940b0cf73e75d6f1fa05345129eb383d2c05a4b809da9d3462c776ccea23d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0W8hfO9H3wvMI1tt16KEjT60YCDmeNk9o9tIF6K0x7XilmYI3WR8Y+aml/TQ2DJBnJaO+X4bFQX4zVQZMSu4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:28:07.383380Z","bundle_sha256":"60b24fd42cebfe6cc64025c23a75afc12544fbf4b5d75e35a78889167c94c304"}}