{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6H4U5YG54QTXKQPTMUBYDI625J","short_pith_number":"pith:6H4U5YG5","canonical_record":{"source":{"id":"1906.08312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ae8467201e59f8d20f11ca6a7afa61aca7c658b7c797a35ef293066f82fc2fd","abstract_canon_sha256":"71e09aa15d597126d8f458d0510c67a94efda040a60d87a94032c8127c0d3bd3"},"schema_version":"1.0"},"canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","source":{"kind":"arxiv","id":"1906.08312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08312","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08312v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08312","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"6H4U5YG54QTX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6H4U5YG54QTXKQPT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6H4U5YG5","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6H4U5YG54QTXKQPTMUBYDI625J","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ae8467201e59f8d20f11ca6a7afa61aca7c658b7c797a35ef293066f82fc2fd","abstract_canon_sha256":"71e09aa15d597126d8f458d0510c67a94efda040a60d87a94032c8127c0d3bd3"},"schema_version":"1.0"},"canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.844602Z","signature_b64":"gyv2xGwjrHzS4RQxEQC0nIeUwXA2MYfSLSSvm4k7YCQ1IZpErSiyjOPyi5QdRyDZ9E7AW0d4PqzbsTT2pCVvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","last_reissued_at":"2026-05-17T23:42:52.844039Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.844039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08312","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtfERp1b9e+aXfW/dkzzPJRO2ElE4l4Hi79kc4d6Y/3wu3Ux8+g8oTFNWK1JJC4uy0OW+vzioIcxdFLRCElKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:57:38.035938Z"},"content_sha256":"5a65f3d00a7bdbb3710bada716153455c34c65e1573dec0690fd95d58964f8fa","schema_version":"1.0","event_id":"sha256:5a65f3d00a7bdbb3710bada716153455c34c65e1573dec0690fd95d58964f8fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6H4U5YG54QTXKQPTMUBYDI625J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrated Model-Based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Malik, Danny Nemer, Harlan Seymour, Jiaming Song, Stefano Ermon, Volodymyr Kuleshov","submitted_at":"2019-06-19T19:10:26Z","abstract_excerpt":"Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for model-based reinforcement learning and argues that good uncertainties must be calibrated, i.e. their probabilities should match empirical frequencies of predicted events. We describe a simple way to augment any model-based reinforcement learning agent with a calibrated model and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08312","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6HCCZxMqQ3Hn/JrC/xjEjypy8ef/ob24QAOTFPDIhvq2MeEGkNIV9VxoCXTgsAf3TWVqlt0Iv/5xcMDtPzlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:57:38.036272Z"},"content_sha256":"85eb6f3d4b1b2239ce4bdeaa09196d7aa2a4b1b14d3e8eb8ff5bad0bf515e441","schema_version":"1.0","event_id":"sha256:85eb6f3d4b1b2239ce4bdeaa09196d7aa2a4b1b14d3e8eb8ff5bad0bf515e441"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/bundle.json","state_url":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6H4U5YG54QTXKQPTMUBYDI625J/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":"2026-06-03T08:57:38Z","links":{"resolver":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J","bundle":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/bundle.json","state":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6H4U5YG54QTXKQPTMUBYDI625J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6H4U5YG54QTXKQPTMUBYDI625J","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":"71e09aa15d597126d8f458d0510c67a94efda040a60d87a94032c8127c0d3bd3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","title_canon_sha256":"1ae8467201e59f8d20f11ca6a7afa61aca7c658b7c797a35ef293066f82fc2fd"},"schema_version":"1.0","source":{"id":"1906.08312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08312","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08312v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08312","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"6H4U5YG54QTX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6H4U5YG54QTXKQPT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6H4U5YG5","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:85eb6f3d4b1b2239ce4bdeaa09196d7aa2a4b1b14d3e8eb8ff5bad0bf515e441","target":"graph","created_at":"2026-05-17T23:42:52Z","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":"Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for model-based reinforcement learning and argues that good uncertainties must be calibrated, i.e. their probabilities should match empirical frequencies of predicted events. We describe a simple way to augment any model-based reinforcement learning agent with a calibrated model and","authors_text":"Ali Malik, Danny Nemer, Harlan Seymour, Jiaming Song, Stefano Ermon, Volodymyr Kuleshov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","title":"Calibrated Model-Based Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08312","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":"sha256:5a65f3d00a7bdbb3710bada716153455c34c65e1573dec0690fd95d58964f8fa","target":"record","created_at":"2026-05-17T23:42:52Z","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":"71e09aa15d597126d8f458d0510c67a94efda040a60d87a94032c8127c0d3bd3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","title_canon_sha256":"1ae8467201e59f8d20f11ca6a7afa61aca7c658b7c797a35ef293066f82fc2fd"},"schema_version":"1.0","source":{"id":"1906.08312","kind":"arxiv","version":1}},"canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","first_computed_at":"2026-05-17T23:42:52.844039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:52.844039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gyv2xGwjrHzS4RQxEQC0nIeUwXA2MYfSLSSvm4k7YCQ1IZpErSiyjOPyi5QdRyDZ9E7AW0d4PqzbsTT2pCVvDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:52.844602Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a65f3d00a7bdbb3710bada716153455c34c65e1573dec0690fd95d58964f8fa","sha256:85eb6f3d4b1b2239ce4bdeaa09196d7aa2a4b1b14d3e8eb8ff5bad0bf515e441"],"state_sha256":"b47a8730b99d80d7f6afb7fe01003945077214de82d3a39c7a2e377e12fa76f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+lI4NR3PqJDrZdpXNz/sCz5g6syuZ/m+Aebgu+n5b0UZBvVNwrme5uGFz58b2jXydmXPTeUE5IkKYI52kokBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:57:38.038207Z","bundle_sha256":"12aeab92c2cf9064cfa295438bb18666c54414ca1d18a11a15f2920d24785d57"}}