{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GRM7HK2BEO467B45ZBE4UIJKJK","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":"1af42c0aab2f8bd09bcc18af3d578e93ea5481637de3674a0257a304f66424e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T09:05:29Z","title_canon_sha256":"a4e4f9ad3e72c7739e429cb2febe04b99a3c35ef483c9cce0f29c041fb9ee257"},"schema_version":"1.0","source":{"id":"2605.31034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31034","created_at":"2026-06-01T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31034v1","created_at":"2026-06-01T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31034","created_at":"2026-06-01T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"GRM7HK2BEO46","created_at":"2026-06-01T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"GRM7HK2BEO467B45","created_at":"2026-06-01T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"GRM7HK2B","created_at":"2026-06-01T01:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:cf85a26aa24c49ba060442cd9037254bcde943970e99dfa5e1476b9ffd34c503","target":"graph","created_at":"2026-06-01T01:03:31Z","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/2605.31034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward, regularized by a KL penalty toward a reference policy. These updates do not include explicit mechanisms that track epistemic uncertainty. This paper studies a stylized explanation for why such uncertainty-agnostic updates can nevertheless be effective. We analyze an annealed softmax (Boltzmann) policy that selects actions according to a softmax of","authors_text":"Mohsen Bayati, William Overman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T09:05:29Z","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31034","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":"sha256:941f83add595f6e948357d76d0dcc360e3d1058cfe95a933c791223f054fc031","target":"record","created_at":"2026-06-01T01:03:31Z","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":"1af42c0aab2f8bd09bcc18af3d578e93ea5481637de3674a0257a304f66424e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T09:05:29Z","title_canon_sha256":"a4e4f9ad3e72c7739e429cb2febe04b99a3c35ef483c9cce0f29c041fb9ee257"},"schema_version":"1.0","source":{"id":"2605.31034","kind":"arxiv","version":1}},"canonical_sha256":"3459f3ab4123b9ef879dc849ca212a4aac54b8b90b33b609eb5269032c104b01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3459f3ab4123b9ef879dc849ca212a4aac54b8b90b33b609eb5269032c104b01","first_computed_at":"2026-06-01T01:03:31.932329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:31.932329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uDnkqU5I9BacEtabnJT6Ljx5gYyC7DK2fZaK/hJmPSk252LMiCZakJFV+aB8mtmt9taDfRqRV04jdTR5dwCFAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:31.933075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:941f83add595f6e948357d76d0dcc360e3d1058cfe95a933c791223f054fc031","sha256:cf85a26aa24c49ba060442cd9037254bcde943970e99dfa5e1476b9ffd34c503"],"state_sha256":"028772d4fc887cadbbc389a3bf06279ab183494a7f3413b66855ec3b74e46094"}