{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UWF5DNDXWLJTJA7T3PH4WPS6QK","short_pith_number":"pith:UWF5DNDX","canonical_record":{"source":{"id":"1901.02219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"af3be17c1ddfb1be8478767bdbc84535b032b0cf2649818b552f04623b9e7417","abstract_canon_sha256":"e16608a75b0a5f22ca1a2cce84d3251ff815402fb6d6b523b48bec2cf561318d"},"schema_version":"1.0"},"canonical_sha256":"a58bd1b477b2d33483f3dbcfcb3e5e8286b27a1168bfff39852e9b568202d964","source":{"kind":"arxiv","id":"1901.02219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02219","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02219v1","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02219","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"UWF5DNDXWLJT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UWF5DNDXWLJTJA7T","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UWF5DNDX","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UWF5DNDXWLJTJA7T3PH4WPS6QK","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"af3be17c1ddfb1be8478767bdbc84535b032b0cf2649818b552f04623b9e7417","abstract_canon_sha256":"e16608a75b0a5f22ca1a2cce84d3251ff815402fb6d6b523b48bec2cf561318d"},"schema_version":"1.0"},"canonical_sha256":"a58bd1b477b2d33483f3dbcfcb3e5e8286b27a1168bfff39852e9b568202d964","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.744628Z","signature_b64":"+m719c7jI7uixE88eqTswCW06l0rXufCvxHdWfcwXMFn1VRjHTw0bzZojAZ2E/D/Zw7HKGtfdUxm3Yoc3Tk8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a58bd1b477b2d33483f3dbcfcb3e5e8286b27a1168bfff39852e9b568202d964","last_reissued_at":"2026-05-17T23:56:43.744050Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.744050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02219","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTaQnVfE8CONFxxzwzq6uNxveUf24uE/w3MnKna79b+MZxLOyzz4QIZMC3ABOk2N4LN+PF9LoHYPSyzJpldTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:20:10.360439Z"},"content_sha256":"41e7e6671cb063bb689f93cb0e73360f35043a4e07608f32fc7b31a5721bfa9d","schema_version":"1.0","event_id":"sha256:41e7e6671cb063bb689f93cb0e73360f35043a4e07608f32fc7b31a5721bfa9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UWF5DNDXWLJTJA7T3PH4WPS6QK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Sedlmeier, Claudia Linnhoff-Popien, Lenz Belzner, Thomas Gabor, Thomy Phan","submitted_at":"2019-01-08T09:41:11Z","abstract_excerpt":"We consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples. The focus of our work lies in analyzing the suitability of approximate Bayesian inference methods and related ensembling techniques that generate uncertainty estimates. Although prior work has shown that dropout-based variational inference techniques and bootstrap-based approaches can be used to model epistemic unce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02219","kind":"arxiv","version":1},"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":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqWfoS3YVqZ0byvId95mlWShomxPwcqXIx92U4D8upoC1MKNcHWsID5ohruy0PmdYluSC6aXT/BCEgwYLCY9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:20:10.361249Z"},"content_sha256":"278e6b6f110677243f8b1faf233140d076a4e2987933c1e620345c3844782c64","schema_version":"1.0","event_id":"sha256:278e6b6f110677243f8b1faf233140d076a4e2987933c1e620345c3844782c64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/bundle.json","state_url":"https://pith.science/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/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":"2026-06-08T05:20:10Z","links":{"resolver":"https://pith.science/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK","bundle":"https://pith.science/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/bundle.json","state":"https://pith.science/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWF5DNDXWLJTJA7T3PH4WPS6QK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UWF5DNDXWLJTJA7T3PH4WPS6QK","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":"e16608a75b0a5f22ca1a2cce84d3251ff815402fb6d6b523b48bec2cf561318d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:11Z","title_canon_sha256":"af3be17c1ddfb1be8478767bdbc84535b032b0cf2649818b552f04623b9e7417"},"schema_version":"1.0","source":{"id":"1901.02219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02219","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02219v1","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02219","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"UWF5DNDXWLJT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UWF5DNDXWLJTJA7T","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UWF5DNDX","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:278e6b6f110677243f8b1faf233140d076a4e2987933c1e620345c3844782c64","target":"graph","created_at":"2026-05-17T23:56:43Z","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 consider the problem of detecting out-of-distribution (OOD) samples in deep reinforcement learning. In a value based reinforcement learning setting, we propose to use uncertainty estimation techniques directly on the agent's value estimating neural network to detect OOD samples. The focus of our work lies in analyzing the suitability of approximate Bayesian inference methods and related ensembling techniques that generate uncertainty estimates. Although prior work has shown that dropout-based variational inference techniques and bootstrap-based approaches can be used to model epistemic unce","authors_text":"Andreas Sedlmeier, Claudia Linnhoff-Popien, Lenz Belzner, Thomas Gabor, Thomy Phan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:11Z","title":"Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02219","kind":"arxiv","version":1},"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":"sha256:41e7e6671cb063bb689f93cb0e73360f35043a4e07608f32fc7b31a5721bfa9d","target":"record","created_at":"2026-05-17T23:56:43Z","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":"e16608a75b0a5f22ca1a2cce84d3251ff815402fb6d6b523b48bec2cf561318d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T09:41:11Z","title_canon_sha256":"af3be17c1ddfb1be8478767bdbc84535b032b0cf2649818b552f04623b9e7417"},"schema_version":"1.0","source":{"id":"1901.02219","kind":"arxiv","version":1}},"canonical_sha256":"a58bd1b477b2d33483f3dbcfcb3e5e8286b27a1168bfff39852e9b568202d964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a58bd1b477b2d33483f3dbcfcb3e5e8286b27a1168bfff39852e9b568202d964","first_computed_at":"2026-05-17T23:56:43.744050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:43.744050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+m719c7jI7uixE88eqTswCW06l0rXufCvxHdWfcwXMFn1VRjHTw0bzZojAZ2E/D/Zw7HKGtfdUxm3Yoc3Tk8AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:43.744628Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e7e6671cb063bb689f93cb0e73360f35043a4e07608f32fc7b31a5721bfa9d","sha256:278e6b6f110677243f8b1faf233140d076a4e2987933c1e620345c3844782c64"],"state_sha256":"b96a5f40a949b35635f988f4f227b76dcb183638b260b1e4d56df9c5bb4cf0c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OX92bEAa6gG7IDMlW2f68mNaj6Ux/ztJstF6PWz6Y8Te6QSJtPPexuBHR2GEPmn4mckg7cRaoiUi4sYzedHNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:20:10.365259Z","bundle_sha256":"59cc294b904709bcffa990f0d64015baac1b157d9b88595e9035b229fa3a1b30"}}