{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PS7C4WLSPQPXA47TOUOAUHNPF5","short_pith_number":"pith:PS7C4WLS","canonical_record":{"source":{"id":"2601.21094","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T22:28:17Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"e94ddb622372968de83643c3530cab8dc4d65286870f1998b0354eead7584f6d","abstract_canon_sha256":"67bab9a4f07c4642b924ba5cff5d7c60d0e4e82781c9b6bf471c8350c2f7a7ce"},"schema_version":"1.0"},"canonical_sha256":"7cbe2e59727c1f7073f3751c0a1daf2f61f49e5c9a81ea710c0b65ac4950e188","source":{"kind":"arxiv","id":"2601.21094","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21094","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21094v2","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21094","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"PS7C4WLSPQPX","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"PS7C4WLSPQPXA47T","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"PS7C4WLS","created_at":"2026-05-26T02:04:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PS7C4WLSPQPXA47TOUOAUHNPF5","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21094","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T22:28:17Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"e94ddb622372968de83643c3530cab8dc4d65286870f1998b0354eead7584f6d","abstract_canon_sha256":"67bab9a4f07c4642b924ba5cff5d7c60d0e4e82781c9b6bf471c8350c2f7a7ce"},"schema_version":"1.0"},"canonical_sha256":"7cbe2e59727c1f7073f3751c0a1daf2f61f49e5c9a81ea710c0b65ac4950e188","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:03.753249Z","signature_b64":"fNEJRiBUscA713Wcncln3sDdc3k0cZU/Z45mDNK6mtpr6//J4zpebEuztoDBRh1vBI/IsJoMm5lYEXjdCOOvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cbe2e59727c1f7073f3751c0a1daf2f61f49e5c9a81ea710c0b65ac4950e188","last_reissued_at":"2026-05-26T02:04:03.752578Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:03.752578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21094","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":"2026-05-26T02:04:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaEnkITe5bs1V5DaHfNnZoOxhe0n+1tUpTXIKh3zy6EEDzLdm0G6zy46JbhQJ0ct69v7/lQ9nSt4byiBPmZ6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:30:52.285298Z"},"content_sha256":"7c6280ebcaae3ef685facf6e2bd65e128edb9f9e9d3f9748cf80921bf5b7e509","schema_version":"1.0","event_id":"sha256:7c6280ebcaae3ef685facf6e2bd65e128edb9f9e9d3f9748cf80921bf5b7e509"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PS7C4WLSPQPXA47TOUOAUHNPF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Josephine Lamp, Lu Feng, Minjae Kwon","submitted_at":"2026-01-28T22:28:17Z","abstract_excerpt":"Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a safety-critical testbed. We benchmark safe RL algorithms on a unified clinical simulator and reveal a safety generalization gap: policies satisfying constraints during training frequently violate safety requirements on unseen patients. We demonstrate that test-time shielding, which filters unsafe actions using learned dynamics models, effectively restores safety"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21094","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/2601.21094/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":"2026-05-26T02:04:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXcykc8hcSSOjQrZAzGb7Hs7/4OJ1Cge8YzikOOOwlAH9vvXdIAtr+GB0IKL0IUYY0Z+PHD8QsJZBCVs0JI3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:30:52.285691Z"},"content_sha256":"a270d681e8bb882c3a676e1ef4cc33cb702d7786fa204dd29ce667f5eb5c2ca5","schema_version":"1.0","event_id":"sha256:a270d681e8bb882c3a676e1ef4cc33cb702d7786fa204dd29ce667f5eb5c2ca5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/bundle.json","state_url":"https://pith.science/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/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":"2026-06-01T10:30:52Z","links":{"resolver":"https://pith.science/pith/PS7C4WLSPQPXA47TOUOAUHNPF5","bundle":"https://pith.science/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/bundle.json","state":"https://pith.science/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PS7C4WLSPQPXA47TOUOAUHNPF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PS7C4WLSPQPXA47TOUOAUHNPF5","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":"67bab9a4f07c4642b924ba5cff5d7c60d0e4e82781c9b6bf471c8350c2f7a7ce","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T22:28:17Z","title_canon_sha256":"e94ddb622372968de83643c3530cab8dc4d65286870f1998b0354eead7584f6d"},"schema_version":"1.0","source":{"id":"2601.21094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21094","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21094v2","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21094","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"PS7C4WLSPQPX","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"PS7C4WLSPQPXA47T","created_at":"2026-05-26T02:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"PS7C4WLS","created_at":"2026-05-26T02:04:03Z"}],"graph_snapshots":[{"event_id":"sha256:a270d681e8bb882c3a676e1ef4cc33cb702d7786fa204dd29ce667f5eb5c2ca5","target":"graph","created_at":"2026-05-26T02:04:03Z","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/2601.21094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a safety-critical testbed. We benchmark safe RL algorithms on a unified clinical simulator and reveal a safety generalization gap: policies satisfying constraints during training frequently violate safety requirements on unseen patients. We demonstrate that test-time shielding, which filters unsafe actions using learned dynamics models, effectively restores safety","authors_text":"Josephine Lamp, Lu Feng, Minjae Kwon","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T22:28:17Z","title":"Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21094","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":"sha256:7c6280ebcaae3ef685facf6e2bd65e128edb9f9e9d3f9748cf80921bf5b7e509","target":"record","created_at":"2026-05-26T02:04:03Z","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":"67bab9a4f07c4642b924ba5cff5d7c60d0e4e82781c9b6bf471c8350c2f7a7ce","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-28T22:28:17Z","title_canon_sha256":"e94ddb622372968de83643c3530cab8dc4d65286870f1998b0354eead7584f6d"},"schema_version":"1.0","source":{"id":"2601.21094","kind":"arxiv","version":2}},"canonical_sha256":"7cbe2e59727c1f7073f3751c0a1daf2f61f49e5c9a81ea710c0b65ac4950e188","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cbe2e59727c1f7073f3751c0a1daf2f61f49e5c9a81ea710c0b65ac4950e188","first_computed_at":"2026-05-26T02:04:03.752578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:03.752578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNEJRiBUscA713Wcncln3sDdc3k0cZU/Z45mDNK6mtpr6//J4zpebEuztoDBRh1vBI/IsJoMm5lYEXjdCOOvCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:03.753249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c6280ebcaae3ef685facf6e2bd65e128edb9f9e9d3f9748cf80921bf5b7e509","sha256:a270d681e8bb882c3a676e1ef4cc33cb702d7786fa204dd29ce667f5eb5c2ca5"],"state_sha256":"709cbd3ed18c31425730f9e00e00734e66aa3c0a40ae052d5f87149954ab29d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZjjVcrmDqo20lT9QQxO6lMeissxUOdxXy4/KK9zJheGLMfyugiDQksaoLH8jQQhayzkNqg3wvxSdCpoaeOuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:30:52.287660Z","bundle_sha256":"6a4ee3a50e7035fc4255f42463cd1fe1a66cad2c94d1cbe06ec488407327665d"}}