{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WEJ3KGHCSAWCOMF7DO4OCCBXYV","short_pith_number":"pith:WEJ3KGHC","canonical_record":{"source":{"id":"1807.06096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-16T20:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"e1e8db47da002e7db3ef0d1c2413692e99f545580659040514d3210abc5f92ca","abstract_canon_sha256":"3e19b4a81f6b82f3abf7cb7ce0256bb428b05705ffdd88afc9d8b4a63d094930"},"schema_version":"1.0"},"canonical_sha256":"b113b518e2902c2730bf1bb8e10837c57d9d7effda176739258dff27b2f16508","source":{"kind":"arxiv","id":"1807.06096","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06096","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06096v2","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06096","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_12","alias_value":"WEJ3KGHCSAWC","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_16","alias_value":"WEJ3KGHCSAWCOMF7","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_8","alias_value":"WEJ3KGHC","created_at":"2026-07-05T00:21:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WEJ3KGHCSAWCOMF7DO4OCCBXYV","target":"record","payload":{"canonical_record":{"source":{"id":"1807.06096","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-16T20:29:04Z","cross_cats_sorted":[],"title_canon_sha256":"e1e8db47da002e7db3ef0d1c2413692e99f545580659040514d3210abc5f92ca","abstract_canon_sha256":"3e19b4a81f6b82f3abf7cb7ce0256bb428b05705ffdd88afc9d8b4a63d094930"},"schema_version":"1.0"},"canonical_sha256":"b113b518e2902c2730bf1bb8e10837c57d9d7effda176739258dff27b2f16508","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:31.365081Z","signature_b64":"HNkjayhaVHb0XYTyHL8eJOiKd9mYfSxrNZjVA8zXraebwq4/i05hAJaLayw6IK3Lb8M6MnhvKnw7O12PgGxqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b113b518e2902c2730bf1bb8e10837c57d9d7effda176739258dff27b2f16508","last_reissued_at":"2026-07-05T00:21:31.364624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:31.364624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.06096","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":"2026-07-05T00:21:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IT0/b6A0H3dzCcARggSr8j+0wLfKCcVgNMKmCFBPu2lAsx9JkTHzoD7wu4LIaOD94fiUEdY8P6ePk1KYjdUYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:03:41.783151Z"},"content_sha256":"368813b1c4bcd33fe95dd0fe62dd598988f9a04a16999bf54f905c96c5ac4d7d","schema_version":"1.0","event_id":"sha256:368813b1c4bcd33fe95dd0fe62dd598988f9a04a16999bf54f905c96c5ac4d7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WEJ3KGHCSAWCOMF7DO4OCCBXYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning via Probabilistic Shields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandru C. Serban, Bettina K\\\"onighofer, Nils Jansen, Roderick Bloem, Sebastian Junges","submitted_at":"2018-07-16T20:29:04Z","abstract_excerpt":"This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning (RL) is a machine learning technique to determine near-optimal policies in MDPs that may be unknown prior to exploring the model. However, during exploration, RL is prone to induce behavior that is undesirable or not allowed in safety- or mission-critical contexts. We introduce the concept of a probabilistic shield that enables decision-making to adhere to s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06096","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/1807.06096/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":"2026-07-05T00:21:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VeWi3H2RmJpwFNsb5wmM4P4GwT8JMNf8HTNf6BUcc8NzspiRyzttkhgueFNivAxHc6mlIrCtSBK4wkhUIFEsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:03:41.783730Z"},"content_sha256":"b6877bbc65bdffe4ea4da6bb448677af2a891f2f828aabf4d79b8697d1289bd9","schema_version":"1.0","event_id":"sha256:b6877bbc65bdffe4ea4da6bb448677af2a891f2f828aabf4d79b8697d1289bd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/bundle.json","state_url":"https://pith.science/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/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":"2026-08-08T11:03:41Z","links":{"resolver":"https://pith.science/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV","bundle":"https://pith.science/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/bundle.json","state":"https://pith.science/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEJ3KGHCSAWCOMF7DO4OCCBXYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WEJ3KGHCSAWCOMF7DO4OCCBXYV","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":"3e19b4a81f6b82f3abf7cb7ce0256bb428b05705ffdd88afc9d8b4a63d094930","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-16T20:29:04Z","title_canon_sha256":"e1e8db47da002e7db3ef0d1c2413692e99f545580659040514d3210abc5f92ca"},"schema_version":"1.0","source":{"id":"1807.06096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06096","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06096v2","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06096","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_12","alias_value":"WEJ3KGHCSAWC","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_16","alias_value":"WEJ3KGHCSAWCOMF7","created_at":"2026-07-05T00:21:31Z"},{"alias_kind":"pith_short_8","alias_value":"WEJ3KGHC","created_at":"2026-07-05T00:21:31Z"}],"graph_snapshots":[{"event_id":"sha256:b6877bbc65bdffe4ea4da6bb448677af2a891f2f828aabf4d79b8697d1289bd9","target":"graph","created_at":"2026-07-05T00:21:31Z","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/1807.06096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning (RL) is a machine learning technique to determine near-optimal policies in MDPs that may be unknown prior to exploring the model. However, during exploration, RL is prone to induce behavior that is undesirable or not allowed in safety- or mission-critical contexts. We introduce the concept of a probabilistic shield that enables decision-making to adhere to s","authors_text":"Alexandru C. Serban, Bettina K\\\"onighofer, Nils Jansen, Roderick Bloem, Sebastian Junges","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-16T20:29:04Z","title":"Safe Reinforcement Learning via Probabilistic Shields"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06096","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":"sha256:368813b1c4bcd33fe95dd0fe62dd598988f9a04a16999bf54f905c96c5ac4d7d","target":"record","created_at":"2026-07-05T00:21:31Z","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":"3e19b4a81f6b82f3abf7cb7ce0256bb428b05705ffdd88afc9d8b4a63d094930","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-16T20:29:04Z","title_canon_sha256":"e1e8db47da002e7db3ef0d1c2413692e99f545580659040514d3210abc5f92ca"},"schema_version":"1.0","source":{"id":"1807.06096","kind":"arxiv","version":2}},"canonical_sha256":"b113b518e2902c2730bf1bb8e10837c57d9d7effda176739258dff27b2f16508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b113b518e2902c2730bf1bb8e10837c57d9d7effda176739258dff27b2f16508","first_computed_at":"2026-07-05T00:21:31.364624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:31.364624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HNkjayhaVHb0XYTyHL8eJOiKd9mYfSxrNZjVA8zXraebwq4/i05hAJaLayw6IK3Lb8M6MnhvKnw7O12PgGxqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:31.365081Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.06096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:368813b1c4bcd33fe95dd0fe62dd598988f9a04a16999bf54f905c96c5ac4d7d","sha256:b6877bbc65bdffe4ea4da6bb448677af2a891f2f828aabf4d79b8697d1289bd9"],"state_sha256":"fd17b5eb57dfe08a9411b431a40a6789caab294063be6b77ef611a2df4617eef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdhtkCUeo9XoIjQNCDoEfvNGGg8uqB+ph3AiZGtdhuI/gHYIOC6ZQ+437/QjjSRhTI8WEmG6HLz5442G2wSZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:03:41.787305Z","bundle_sha256":"c93b08c3c75c157816706ae20f8d0910fca9e735eca1bf55458f17b6c517410a"}}