{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7AM2RFVPQH7GY7X7A3B6YN36CI","short_pith_number":"pith:7AM2RFVP","canonical_record":{"source":{"id":"1910.10885","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-24T02:22:42Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"2ce773969b9738778d79f1bf6a2a4efc69bd67cfa5ad0f4199bc17a07f6e8147","abstract_canon_sha256":"b2448919d27e80e63d6717e93eb5a38bfd50b0c9d76e754f14b89a6e7b15bf87"},"schema_version":"1.0"},"canonical_sha256":"f819a896af81fe6c7eff06c3ec377e1200dc5c5c1897029c75c1afd2ba7b1cd0","source":{"kind":"arxiv","id":"1910.10885","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10885","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10885v2","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10885","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"7AM2RFVPQH7G","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"7AM2RFVPQH7GY7X7","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"7AM2RFVP","created_at":"2026-07-05T00:35:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7AM2RFVPQH7GY7X7A3B6YN36CI","target":"record","payload":{"canonical_record":{"source":{"id":"1910.10885","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-24T02:22:42Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"2ce773969b9738778d79f1bf6a2a4efc69bd67cfa5ad0f4199bc17a07f6e8147","abstract_canon_sha256":"b2448919d27e80e63d6717e93eb5a38bfd50b0c9d76e754f14b89a6e7b15bf87"},"schema_version":"1.0"},"canonical_sha256":"f819a896af81fe6c7eff06c3ec377e1200dc5c5c1897029c75c1afd2ba7b1cd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:34.031805Z","signature_b64":"jK5nY7JTOd/5Pp/16YjXvx9lMgyCcJqynMwxCb+QKGd+gqff3SFTofu8dGEDjT64Bex1yRblfhiTzZaHleioCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f819a896af81fe6c7eff06c3ec377e1200dc5c5c1897029c75c1afd2ba7b1cd0","last_reissued_at":"2026-07-05T00:35:34.031352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:34.031352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.10885","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":"2026-07-05T00:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fKx26GMwO4jbfhLW0HgPrCfrJeT/jXtKlJ9Y2a6ccyV19LP+xfdJ+Bs5NWixEyG7z1PvVg8OGjQ4iQRBBIeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:30.054159Z"},"content_sha256":"473a5b68e53e6286685c018e50e8d858a4491cd057aaee553f361512725e2c3c","schema_version":"1.0","event_id":"sha256:473a5b68e53e6286685c018e50e8d858a4491cd057aaee553f361512725e2c3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7AM2RFVPQH7GY7X7A3B6YN36CI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Osbert Bastani, Shuo Li","submitted_at":"2019-10-24T02:22:42Z","abstract_excerpt":"This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known, and are subject to additive stochastic disturbances with known distribution. Our goal is to ensure the safety of a control policy trained using reinforcement learning, e.g., in a simulated environment. We build on the idea of model predictive shielding (MPS), where a backup controller is used to override the learned policy as needed to ensure safety. The key challenge is how to compute a backup policy in the contex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10885","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/1910.10885/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":"2026-07-05T00:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVFdO8AMXqe9NgIR1Jd4/sls6lWu1ik7qwcQ/16CVmTwg3sU+6jE2a3mzPo13dM4hR86jHe1HkSS8W/DcfXhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:30.054555Z"},"content_sha256":"6c905b1a8adcf338df5025749bd4e521e1e00e6d6546091c5459a36b97bd5a73","schema_version":"1.0","event_id":"sha256:6c905b1a8adcf338df5025749bd4e521e1e00e6d6546091c5459a36b97bd5a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/bundle.json","state_url":"https://pith.science/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/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":"2026-07-07T12:31:30Z","links":{"resolver":"https://pith.science/pith/7AM2RFVPQH7GY7X7A3B6YN36CI","bundle":"https://pith.science/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/bundle.json","state":"https://pith.science/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7AM2RFVPQH7GY7X7A3B6YN36CI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7AM2RFVPQH7GY7X7A3B6YN36CI","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":"b2448919d27e80e63d6717e93eb5a38bfd50b0c9d76e754f14b89a6e7b15bf87","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-24T02:22:42Z","title_canon_sha256":"2ce773969b9738778d79f1bf6a2a4efc69bd67cfa5ad0f4199bc17a07f6e8147"},"schema_version":"1.0","source":{"id":"1910.10885","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10885","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10885v2","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10885","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"7AM2RFVPQH7G","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"7AM2RFVPQH7GY7X7","created_at":"2026-07-05T00:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"7AM2RFVP","created_at":"2026-07-05T00:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:6c905b1a8adcf338df5025749bd4e521e1e00e6d6546091c5459a36b97bd5a73","target":"graph","created_at":"2026-07-05T00:35:34Z","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/1910.10885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known, and are subject to additive stochastic disturbances with known distribution. Our goal is to ensure the safety of a control policy trained using reinforcement learning, e.g., in a simulated environment. We build on the idea of model predictive shielding (MPS), where a backup controller is used to override the learned policy as needed to ensure safety. The key challenge is how to compute a backup policy in the contex","authors_text":"Osbert Bastani, Shuo Li","cross_cats":["cs.LG","cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-24T02:22:42Z","title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10885","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":"sha256:473a5b68e53e6286685c018e50e8d858a4491cd057aaee553f361512725e2c3c","target":"record","created_at":"2026-07-05T00:35:34Z","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":"b2448919d27e80e63d6717e93eb5a38bfd50b0c9d76e754f14b89a6e7b15bf87","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-24T02:22:42Z","title_canon_sha256":"2ce773969b9738778d79f1bf6a2a4efc69bd67cfa5ad0f4199bc17a07f6e8147"},"schema_version":"1.0","source":{"id":"1910.10885","kind":"arxiv","version":2}},"canonical_sha256":"f819a896af81fe6c7eff06c3ec377e1200dc5c5c1897029c75c1afd2ba7b1cd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f819a896af81fe6c7eff06c3ec377e1200dc5c5c1897029c75c1afd2ba7b1cd0","first_computed_at":"2026-07-05T00:35:34.031352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:34.031352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jK5nY7JTOd/5Pp/16YjXvx9lMgyCcJqynMwxCb+QKGd+gqff3SFTofu8dGEDjT64Bex1yRblfhiTzZaHleioCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:34.031805Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.10885","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:473a5b68e53e6286685c018e50e8d858a4491cd057aaee553f361512725e2c3c","sha256:6c905b1a8adcf338df5025749bd4e521e1e00e6d6546091c5459a36b97bd5a73"],"state_sha256":"a94921280c8c797aefd805e9d526f2655ce4028b00ebd5d9a6723e0398acb38d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1q5GP9WifgetCyFlMgsEMVtJJBrCj+FOqp1AIp2myyQhUHtLRNwyiss7032ObJuVofXFxPZAf2NwbjCh3mlPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:31:30.056860Z","bundle_sha256":"fe85d1539631180911540eeb6eb34edd4d795255351bb35784cbe85463b327c6"}}