{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5OKHDN6TZ2JIKMWXFEUIDQ36CI","short_pith_number":"pith:5OKHDN6T","canonical_record":{"source":{"id":"1803.10231","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d9d45c098399ed6c0db462a85e513cd78b240e2efdd4efbd1c66a18e405b8f4","abstract_canon_sha256":"180a79ccee3b58305cd96f8e7d5db88326b674c1f783b575fe96c5ebe119f7c9"},"schema_version":"1.0"},"canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","source":{"kind":"arxiv","id":"1803.10231","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10231","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10231v3","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10231","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"pith_short_12","alias_value":"5OKHDN6TZ2JI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5OKHDN6TZ2JIKMWX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5OKHDN6T","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5OKHDN6TZ2JIKMWXFEUIDQ36CI","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10231","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d9d45c098399ed6c0db462a85e513cd78b240e2efdd4efbd1c66a18e405b8f4","abstract_canon_sha256":"180a79ccee3b58305cd96f8e7d5db88326b674c1f783b575fe96c5ebe119f7c9"},"schema_version":"1.0"},"canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:57.813766Z","signature_b64":"ZgI6SHPorGfN5xgCM1Ml8jJGj+Z77V48r8PH88tJh4KDiN+gnVTvBxU8wM+UuKZUKeETNIHH71sWrsuoWwxZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","last_reissued_at":"2026-05-17T23:53:57.813086Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:57.813086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10231","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPM623kN+dy7+WtujXqaM2MrRO5a9CDczqiZpGwhjmDadorlQCoP7XjjPTmYbrrvYly+CusEiheh4Kh7Klj2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:57:55.688101Z"},"content_sha256":"2ab3abd779c1a021442d11969bd86b9c5d5781118b4e2e09dbb88d35f4fecd65","schema_version":"1.0","event_id":"sha256:2ab3abd779c1a021442d11969bd86b9c5d5781118b4e2e09dbb88d35f4fecd65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5OKHDN6TZ2JIKMWXFEUIDQ36CI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe end-to-end imitation learning for model predictive control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Evangelos A. Theodorou, Kamil Saigol, Keuntaek Lee","submitted_at":"2018-03-27T15:47:29Z","abstract_excerpt":"We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imitation learning to simultaneously learn a control policy as well as a threshold over the predictive uncertainty of the learned model, with no hand-tuning required. Corrective action, such as a return of control to the model predictive controller or human expert, is taken when the u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10231","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:53:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0T74GA5FD3WVT1474WO3NBzAoFQRU5+Y/2TrE/lQ+GZy6kehFdZ4VukDWqQ+NnuBB7Hkdq4SBBTF0DLnn5JMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:57:55.688481Z"},"content_sha256":"852c04e3f8b55cc7f8b479de6b1f9eea813af52d6bb5c67a22127bf04026cfc0","schema_version":"1.0","event_id":"sha256:852c04e3f8b55cc7f8b479de6b1f9eea813af52d6bb5c67a22127bf04026cfc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/bundle.json","state_url":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/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":"2026-05-28T04:57:55Z","links":{"resolver":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI","bundle":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/bundle.json","state":"https://pith.science/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OKHDN6TZ2JIKMWXFEUIDQ36CI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5OKHDN6TZ2JIKMWXFEUIDQ36CI","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":"180a79ccee3b58305cd96f8e7d5db88326b674c1f783b575fe96c5ebe119f7c9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","title_canon_sha256":"6d9d45c098399ed6c0db462a85e513cd78b240e2efdd4efbd1c66a18e405b8f4"},"schema_version":"1.0","source":{"id":"1803.10231","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10231","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10231v3","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10231","created_at":"2026-05-17T23:53:57Z"},{"alias_kind":"pith_short_12","alias_value":"5OKHDN6TZ2JI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5OKHDN6TZ2JIKMWX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5OKHDN6T","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:852c04e3f8b55cc7f8b479de6b1f9eea813af52d6bb5c67a22127bf04026cfc0","target":"graph","created_at":"2026-05-17T23:53:57Z","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"},"paper":{"abstract_excerpt":"We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imitation learning to simultaneously learn a control policy as well as a threshold over the predictive uncertainty of the learned model, with no hand-tuning required. Corrective action, such as a return of control to the model predictive controller or human expert, is taken when the u","authors_text":"Evangelos A. Theodorou, Kamil Saigol, Keuntaek Lee","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","title":"Safe end-to-end imitation learning for model predictive control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10231","kind":"arxiv","version":3},"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":"sha256:2ab3abd779c1a021442d11969bd86b9c5d5781118b4e2e09dbb88d35f4fecd65","target":"record","created_at":"2026-05-17T23:53:57Z","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":"180a79ccee3b58305cd96f8e7d5db88326b674c1f783b575fe96c5ebe119f7c9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-27T15:47:29Z","title_canon_sha256":"6d9d45c098399ed6c0db462a85e513cd78b240e2efdd4efbd1c66a18e405b8f4"},"schema_version":"1.0","source":{"id":"1803.10231","kind":"arxiv","version":3}},"canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb9471b7d3ce928532d7292881c37e12068a2e090472c86c8a211dae35f7a885","first_computed_at":"2026-05-17T23:53:57.813086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:57.813086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZgI6SHPorGfN5xgCM1Ml8jJGj+Z77V48r8PH88tJh4KDiN+gnVTvBxU8wM+UuKZUKeETNIHH71sWrsuoWwxZDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:57.813766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10231","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ab3abd779c1a021442d11969bd86b9c5d5781118b4e2e09dbb88d35f4fecd65","sha256:852c04e3f8b55cc7f8b479de6b1f9eea813af52d6bb5c67a22127bf04026cfc0"],"state_sha256":"edb5d475fdee63fb1a079709ddcfeb6bb4f9195e347b83c8e01df6ee4dd97023"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNtp3StZN8FMHWRvos/q4Nu/neqUQd3ON/LXTAgflV+cyaP/oA7R91oH2OeVp/Jb6yr89XC0VNylG/lwwsWhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:57:55.690544Z","bundle_sha256":"13a62be9dfca829c2825f23879cf6eeb2ab15ed6f079a8a4e10327ecd081aacc"}}