{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S7CB65RWPISEOTQ2PGUQAM2JXX","short_pith_number":"pith:S7CB65RW","canonical_record":{"source":{"id":"2312.04386","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T15:55:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9e8fb9520c8f35fd1f26a87f89e9f06ce8699dae06b1d44279f44ee75d1654","abstract_canon_sha256":"35e54778d1d9e22faafc8d7da8da5e9fd394f1e05abd35566734cb5ee42560f9"},"schema_version":"1.0"},"canonical_sha256":"97c41f76367a24474e1a79a9003349bdd2459195335f38223355f77a2c0a9fba","source":{"kind":"arxiv","id":"2312.04386","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04386","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04386v3","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04386","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"S7CB65RWPISE","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"S7CB65RWPISEOTQ2","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"S7CB65RW","created_at":"2026-07-05T09:07:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S7CB65RWPISEOTQ2PGUQAM2JXX","target":"record","payload":{"canonical_record":{"source":{"id":"2312.04386","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T15:55:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9e8fb9520c8f35fd1f26a87f89e9f06ce8699dae06b1d44279f44ee75d1654","abstract_canon_sha256":"35e54778d1d9e22faafc8d7da8da5e9fd394f1e05abd35566734cb5ee42560f9"},"schema_version":"1.0"},"canonical_sha256":"97c41f76367a24474e1a79a9003349bdd2459195335f38223355f77a2c0a9fba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:44.739463Z","signature_b64":"X4MSxE80r8pjRhUvOma4WYCgQ33UC81N/VpjQnUYARpthmaj+XNTQNL+LLQ8VYG43l3bLJdsvNUOYry+/+d1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c41f76367a24474e1a79a9003349bdd2459195335f38223355f77a2c0a9fba","last_reissued_at":"2026-07-05T09:07:44.738945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:44.738945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.04386","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":"2026-07-05T09:07:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0Wt8p+gFXFG5IaYpZ803eV88Y3PbwfZ44U7k9DVmn/lpG9cOcIxSk5YPLcLoGldBh+1Ulql/Z+dLGKpXeqiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:39:20.204391Z"},"content_sha256":"47515d58a7c926a51ccb4eb10403fc68b78e02c66e500e7818ac010a32d1e657","schema_version":"1.0","event_id":"sha256:47515d58a7c926a51ccb4eb10403fc68b78e02c66e500e7818ac010a32d1e657"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S7CB65RWPISEOTQ2PGUQAM2JXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro G. Bottero, Carlos E. Luis, Felix Berkenkamp, Jan Peters, Julia Vinogradska","submitted_at":"2023-12-07T15:55:58Z","abstract_excerpt":"We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance over values induced by a distribution over Markov decision processes (MDPs). Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation (UBE), but the over-approximation may result in inefficient exploration. We propose a new UBE whose solution converges to the true posterior variance over values and leads to lower regret in tabular exploration problems. We identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04386","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.04386/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:07:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZiU3LuucyiosLVHKxKM7au4Qh4AY2p68bwZagwYccadYpZ7i5re/sQafNQMwyASOmgwFYUNfJxcqj2zumBuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:39:20.204715Z"},"content_sha256":"c4dd55e49ceae574ee4581da67787369fae91461cfeb3e9735f683545e120493","schema_version":"1.0","event_id":"sha256:c4dd55e49ceae574ee4581da67787369fae91461cfeb3e9735f683545e120493"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/bundle.json","state_url":"https://pith.science/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/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":"2026-08-11T12:39:20Z","links":{"resolver":"https://pith.science/pith/S7CB65RWPISEOTQ2PGUQAM2JXX","bundle":"https://pith.science/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/bundle.json","state":"https://pith.science/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7CB65RWPISEOTQ2PGUQAM2JXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S7CB65RWPISEOTQ2PGUQAM2JXX","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":"35e54778d1d9e22faafc8d7da8da5e9fd394f1e05abd35566734cb5ee42560f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T15:55:58Z","title_canon_sha256":"bc9e8fb9520c8f35fd1f26a87f89e9f06ce8699dae06b1d44279f44ee75d1654"},"schema_version":"1.0","source":{"id":"2312.04386","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04386","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04386v3","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04386","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"S7CB65RWPISE","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"S7CB65RWPISEOTQ2","created_at":"2026-07-05T09:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"S7CB65RW","created_at":"2026-07-05T09:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:c4dd55e49ceae574ee4581da67787369fae91461cfeb3e9735f683545e120493","target":"graph","created_at":"2026-07-05T09:07:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.04386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance over values induced by a distribution over Markov decision processes (MDPs). Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation (UBE), but the over-approximation may result in inefficient exploration. We propose a new UBE whose solution converges to the true posterior variance over values and leads to lower regret in tabular exploration problems. We identif","authors_text":"Alessandro G. Bottero, Carlos E. Luis, Felix Berkenkamp, Jan Peters, Julia Vinogradska","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T15:55:58Z","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04386","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":"sha256:47515d58a7c926a51ccb4eb10403fc68b78e02c66e500e7818ac010a32d1e657","target":"record","created_at":"2026-07-05T09:07:44Z","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":"35e54778d1d9e22faafc8d7da8da5e9fd394f1e05abd35566734cb5ee42560f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T15:55:58Z","title_canon_sha256":"bc9e8fb9520c8f35fd1f26a87f89e9f06ce8699dae06b1d44279f44ee75d1654"},"schema_version":"1.0","source":{"id":"2312.04386","kind":"arxiv","version":3}},"canonical_sha256":"97c41f76367a24474e1a79a9003349bdd2459195335f38223355f77a2c0a9fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97c41f76367a24474e1a79a9003349bdd2459195335f38223355f77a2c0a9fba","first_computed_at":"2026-07-05T09:07:44.738945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:44.738945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X4MSxE80r8pjRhUvOma4WYCgQ33UC81N/VpjQnUYARpthmaj+XNTQNL+LLQ8VYG43l3bLJdsvNUOYry+/+d1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:44.739463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04386","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47515d58a7c926a51ccb4eb10403fc68b78e02c66e500e7818ac010a32d1e657","sha256:c4dd55e49ceae574ee4581da67787369fae91461cfeb3e9735f683545e120493"],"state_sha256":"f862937c7b46bfd5fc12435386d00a3db8cc5822687a22520020044b595a0a8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjQBYhWdIa1hodXLhs5J3McaDOenvnDNTET28cWaRlFmyURjTidVwGBXjRcd8Mrj5swJJXnDSv7/Svix075gDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:39:20.207038Z","bundle_sha256":"a945f256841c7f8bd5e32a789fd76fa6126de4be1c5fefa77a2d8afd1322aa50"}}