{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6AS377BWJQGMKPRYRGS5ERWLB","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":"d552bb634f09c8b09064e3e23e78e85dcef23d78a302de974a86457bd5178f14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T12:38:19Z","title_canon_sha256":"4f62b8d8103fee99d9bc318133a6ce3a17620531259f6f5b823181291dfe66fe"},"schema_version":"1.0","source":{"id":"2505.21119","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21119","created_at":"2026-07-05T11:14:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21119v2","created_at":"2026-07-05T11:14:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21119","created_at":"2026-07-05T11:14:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z6AS377BWJQG","created_at":"2026-07-05T11:14:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z6AS377BWJQGMKPR","created_at":"2026-07-05T11:14:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z6AS377B","created_at":"2026-07-05T11:14:08Z"}],"graph_snapshots":[{"event_id":"sha256:77fcb96dac8fd4e11670d62fdd1a52f1680a0e733a83dc6e8bfd80b69621ce7a","target":"graph","created_at":"2026-07-05T11:14:08Z","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/2505.21119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimating epistemic uncertainty in value functions is a crucial challenge for many aspects of reinforcement learning (RL), including efficient exploration, safe decision-making, and offline RL. While deep ensembles provide a robust method for quantifying value uncertainty, they come with significant computational overhead. Single-model methods, while computationally favorable, often rely on heuristics and typically require additional propagation mechanisms for myopic uncertainty estimates. In this work we introduce universal value-function uncertainties (UVU), which, similar in spirit to rand","authors_text":"Caroline Horsch, Matthijs T. J. Spaan, Max Weltevrede, Moritz A. Zanger, Pascal R. van der Vaart, Wendelin B\\\"ohmer, Yaniv Oren","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T12:38:19Z","title":"Universal Value-Function Uncertainties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21119","kind":"arxiv","version":2},"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":"sha256:8d3eb5c15fb70165cf42cfe02df8e81889572b904e44ed4cb8b76deb484b291d","target":"record","created_at":"2026-07-05T11:14:08Z","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":"d552bb634f09c8b09064e3e23e78e85dcef23d78a302de974a86457bd5178f14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T12:38:19Z","title_canon_sha256":"4f62b8d8103fee99d9bc318133a6ce3a17620531259f6f5b823181291dfe66fe"},"schema_version":"1.0","source":{"id":"2505.21119","kind":"arxiv","version":2}},"canonical_sha256":"cf812dffe1b2606629f1c44d2e9236587fb4e13f0e5ca14d6b0cdec3765cfd92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf812dffe1b2606629f1c44d2e9236587fb4e13f0e5ca14d6b0cdec3765cfd92","first_computed_at":"2026-07-05T11:14:08.077734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:08.077734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62IO3SgHMUS6Ia8dCjdIuJjEIHOyxjiFPZyRLR82zp2IoCyPXuYM6F2ShnrPQbegc1KRnmDE3gNy+ANxcTPFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:08.078179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21119","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d3eb5c15fb70165cf42cfe02df8e81889572b904e44ed4cb8b76deb484b291d","sha256:77fcb96dac8fd4e11670d62fdd1a52f1680a0e733a83dc6e8bfd80b69621ce7a"],"state_sha256":"345fa5153a4b10b683f0d24223090ed72e9343b8d0f7576f95de65cbee15d758"}