{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QQ64XO4JWYFDUSJSNYGZC6UMBV","short_pith_number":"pith:QQ64XO4J","schema_version":"1.0","canonical_sha256":"843dcbbb89b60a3a49326e0d917a8c0d576f86f7a2dcc8d8e24d82ed322647fc","source":{"kind":"arxiv","id":"1810.08700","version":2},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning with Model Uncertainty Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bj\\\"orn L\\\"utjens, Jonathan P. How, Michael Everett","submitted_at":"2018-10-19T22:04:59Z","abstract_excerpt":"Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly int"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1810.08700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-19T22:04:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eebb59900ffd078e5fd0720849a270a6581fc88aff97c93fb44b561822116cb1","abstract_canon_sha256":"88f984419b6af5f424598ca536165dd3494787eb254ee01bde25af0c0d6e2c16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:21.926265Z","signature_b64":"BnskwaQe82PfBC2hj8jPGkLresW6M95hxBgXbsVu8ee2EGZFtO5ZAtODRICckrX9VOWqn6fxooHhIqPBxy19DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843dcbbb89b60a3a49326e0d917a8c0d576f86f7a2dcc8d8e24d82ed322647fc","last_reissued_at":"2026-05-17T23:52:21.925536Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:21.925536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning with Model Uncertainty Estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bj\\\"orn L\\\"utjens, Jonathan P. How, Michael Everett","submitted_at":"2018-10-19T22:04:59Z","abstract_excerpt":"Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08700","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.08700","created_at":"2026-05-17T23:52:21.925656+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08700v2","created_at":"2026-05-17T23:52:21.925656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08700","created_at":"2026-05-17T23:52:21.925656+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQ64XO4JWYFD","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQ64XO4JWYFDUSJS","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQ64XO4J","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV","json":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV.json","graph_json":"https://pith.science/api/pith-number/QQ64XO4JWYFDUSJSNYGZC6UMBV/graph.json","events_json":"https://pith.science/api/pith-number/QQ64XO4JWYFDUSJSNYGZC6UMBV/events.json","paper":"https://pith.science/paper/QQ64XO4J"},"agent_actions":{"view_html":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV","download_json":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV.json","view_paper":"https://pith.science/paper/QQ64XO4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08700&json=true","fetch_graph":"https://pith.science/api/pith-number/QQ64XO4JWYFDUSJSNYGZC6UMBV/graph.json","fetch_events":"https://pith.science/api/pith-number/QQ64XO4JWYFDUSJSNYGZC6UMBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV/action/storage_attestation","attest_author":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV/action/author_attestation","sign_citation":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV/action/citation_signature","submit_replication":"https://pith.science/pith/QQ64XO4JWYFDUSJSNYGZC6UMBV/action/replication_record"}},"created_at":"2026-05-17T23:52:21.925656+00:00","updated_at":"2026-05-17T23:52:21.925656+00:00"}