{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SLKB4SRK42KFODYTF5MWZ66HZP","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":"e3f08bb578ed55db03b738c4914bed210eb804791cb979a075ddb6d2b86785b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T10:12:42Z","title_canon_sha256":"262ce370be05a32a88248a2c75611d60e3678044c140ad4e9c70c1cd5c9a375f"},"schema_version":"1.0","source":{"id":"2508.21488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21488","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21488v1","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21488","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"SLKB4SRK42KF","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"SLKB4SRK42KFODYT","created_at":"2026-07-05T12:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"SLKB4SRK","created_at":"2026-07-05T12:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:3fbbe64431bd117c7495c3833f5a299bef78950de2768282d10330c87a6c6c20","target":"graph","created_at":"2026-07-05T12:01:35Z","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/2508.21488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty quantification in reinforcement learning can greatly improve exploration and robustness. Approximate Bayesian approaches have recently been popularized to quantify uncertainty in model-free algorithms. However, so far the focus has been on improving the accuracy of the posterior approximation, instead of studying the accuracy of the prior and likelihood assumptions underlying the posterior. In this work, we demonstrate that there is a cold posterior effect in Bayesian deep Q-learning, where contrary to theory, performance increases when reducing the temperature of the posterior. To","authors_text":"Matthijs T.J. Spaan, Neil Yorke-Smith, Pascal R. van der Vaart","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T10:12:42Z","title":"Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21488","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":"sha256:061567d8dd3f2339283576ba10ad185a305e8d4bddab3cfbaa3e71c31a9d6fdf","target":"record","created_at":"2026-07-05T12:01:35Z","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":"e3f08bb578ed55db03b738c4914bed210eb804791cb979a075ddb6d2b86785b4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T10:12:42Z","title_canon_sha256":"262ce370be05a32a88248a2c75611d60e3678044c140ad4e9c70c1cd5c9a375f"},"schema_version":"1.0","source":{"id":"2508.21488","kind":"arxiv","version":1}},"canonical_sha256":"92d41e4a2ae694570f132f596cfbc7cbf7d6f98d348f86a95b959b0e134083d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92d41e4a2ae694570f132f596cfbc7cbf7d6f98d348f86a95b959b0e134083d1","first_computed_at":"2026-07-05T12:01:35.596624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:35.596624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M1tNXnXr2k2tNCvFzENJ+Qyc7zYZoSW5KQZqPeoKt1/d3UmDsMBKCMgBq7i1DgcKnS2Do4C1U7Paya1AmMIFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:35.597111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:061567d8dd3f2339283576ba10ad185a305e8d4bddab3cfbaa3e71c31a9d6fdf","sha256:3fbbe64431bd117c7495c3833f5a299bef78950de2768282d10330c87a6c6c20"],"state_sha256":"08612bad4e39bd67e021d30a12c78dcd10dc784211ccfbf51475a867b845f4f6"}