{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:T4EPN4PINVSCLIQRKCPV3UE5IY","short_pith_number":"pith:T4EPN4PI","canonical_record":{"source":{"id":"1812.10687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T10:36:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5861a0b07bf3e266b6b073cbffb9b1803dad4111ee65e2c1a6ad42977541c4f9","abstract_canon_sha256":"d9e44c01bb14d5a55794802311e1e3742e13a324edcbdb79caa052518c3e9f7e"},"schema_version":"1.0"},"canonical_sha256":"9f08f6f1e86d6425a211509f5dd09d4611ec9609864a383aae7d4e94081e2e6d","source":{"kind":"arxiv","id":"1812.10687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10687","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10687v1","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10687","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"T4EPN4PINVSC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"T4EPN4PINVSCLIQR","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"T4EPN4PI","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:T4EPN4PINVSCLIQRKCPV3UE5IY","target":"record","payload":{"canonical_record":{"source":{"id":"1812.10687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T10:36:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5861a0b07bf3e266b6b073cbffb9b1803dad4111ee65e2c1a6ad42977541c4f9","abstract_canon_sha256":"d9e44c01bb14d5a55794802311e1e3742e13a324edcbdb79caa052518c3e9f7e"},"schema_version":"1.0"},"canonical_sha256":"9f08f6f1e86d6425a211509f5dd09d4611ec9609864a383aae7d4e94081e2e6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:20.282234Z","signature_b64":"1npbjN1uoSrzTAG6njoB+X3Tmt5xtsRlwSLvGaK+rCaf/OTfmFRbZcAiCcLgCV0QQr+Ooaqrz9DJEkAj8SaxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f08f6f1e86d6425a211509f5dd09d4611ec9609864a383aae7d4e94081e2e6d","last_reissued_at":"2026-05-17T23:57:20.281508Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:20.281508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.10687","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":"2026-05-17T23:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0XzxlvCYC8BTCZlKkmdONXUXKQFk93kn/K58YjBVYZF5ghmWe00v4X/33wH7j7lKsRTlfXlyMKw52D+C7ni9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:58:34.858973Z"},"content_sha256":"fbba31e74747c0f53bd1c16629405f88d4bd181be79f0e28814bf5780b3747fe","schema_version":"1.0","event_id":"sha256:fbba31e74747c0f53bd1c16629405f88d4bd181be79f0e28814bf5780b3747fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:T4EPN4PINVSCLIQRKCPV3UE5IY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Kahn, Jeff Clune, Rowan McAllister, Sergey Levine","submitted_at":"2018-12-27T10:36:26Z","abstract_excerpt":"Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but can struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10687","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":"2026-05-17T23:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"07urCqcmr5DIJe4vnHDEdsZRl+ta0aWNexOASd6DPNd+a7EnwYZDoR+8GvGlxdNIxongULqp+sbs6L3ioYmJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:58:34.859335Z"},"content_sha256":"e62635b2777def246b74a01d4d989911f69a3189cddf5a8d1dd132bb794d3286","schema_version":"1.0","event_id":"sha256:e62635b2777def246b74a01d4d989911f69a3189cddf5a8d1dd132bb794d3286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/bundle.json","state_url":"https://pith.science/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/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":"2026-06-03T20:58:34Z","links":{"resolver":"https://pith.science/pith/T4EPN4PINVSCLIQRKCPV3UE5IY","bundle":"https://pith.science/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/bundle.json","state":"https://pith.science/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4EPN4PINVSCLIQRKCPV3UE5IY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:T4EPN4PINVSCLIQRKCPV3UE5IY","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":"d9e44c01bb14d5a55794802311e1e3742e13a324edcbdb79caa052518c3e9f7e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T10:36:26Z","title_canon_sha256":"5861a0b07bf3e266b6b073cbffb9b1803dad4111ee65e2c1a6ad42977541c4f9"},"schema_version":"1.0","source":{"id":"1812.10687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10687","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10687v1","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10687","created_at":"2026-05-17T23:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"T4EPN4PINVSC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"T4EPN4PINVSCLIQR","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"T4EPN4PI","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:e62635b2777def246b74a01d4d989911f69a3189cddf5a8d1dd132bb794d3286","target":"graph","created_at":"2026-05-17T23:57:20Z","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":"Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but can struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low est","authors_text":"Gregory Kahn, Jeff Clune, Rowan McAllister, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T10:36:26Z","title":"Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10687","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:fbba31e74747c0f53bd1c16629405f88d4bd181be79f0e28814bf5780b3747fe","target":"record","created_at":"2026-05-17T23:57:20Z","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":"d9e44c01bb14d5a55794802311e1e3742e13a324edcbdb79caa052518c3e9f7e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-27T10:36:26Z","title_canon_sha256":"5861a0b07bf3e266b6b073cbffb9b1803dad4111ee65e2c1a6ad42977541c4f9"},"schema_version":"1.0","source":{"id":"1812.10687","kind":"arxiv","version":1}},"canonical_sha256":"9f08f6f1e86d6425a211509f5dd09d4611ec9609864a383aae7d4e94081e2e6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f08f6f1e86d6425a211509f5dd09d4611ec9609864a383aae7d4e94081e2e6d","first_computed_at":"2026-05-17T23:57:20.281508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:20.281508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1npbjN1uoSrzTAG6njoB+X3Tmt5xtsRlwSLvGaK+rCaf/OTfmFRbZcAiCcLgCV0QQr+Ooaqrz9DJEkAj8SaxBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:20.282234Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.10687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbba31e74747c0f53bd1c16629405f88d4bd181be79f0e28814bf5780b3747fe","sha256:e62635b2777def246b74a01d4d989911f69a3189cddf5a8d1dd132bb794d3286"],"state_sha256":"4e24524ab630706e0d858fecc9600dd09705ed74ba5ce66214f13740f74a9255"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYW5T3tj2WiAOBWo4e0eHit9vRJNRFvbTYudiPO3HCn/voIVz8K1G36fSLNoXo3N19NYbTjqPzPf+Lfr8Pb5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:58:34.861274Z","bundle_sha256":"9792385432606ec05f44d15ffbd8432db0660b93697f2d66ff72cdaacfc28577"}}