{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JL23K5C4KYG4AF7K53WJJUAY3U","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":"c3b47b74bad2ee05b1732e7d303acded8de2e0849be8931b5a445d39d162695a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T20:50:53Z","title_canon_sha256":"83f20d1a2a7dd4a8c42dd62ef166e8c3217539be6ee78c5edff779e19acf8617"},"schema_version":"1.0","source":{"id":"2508.11800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11800","created_at":"2026-07-05T11:54:54Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11800v1","created_at":"2026-07-05T11:54:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11800","created_at":"2026-07-05T11:54:54Z"},{"alias_kind":"pith_short_12","alias_value":"JL23K5C4KYG4","created_at":"2026-07-05T11:54:54Z"},{"alias_kind":"pith_short_16","alias_value":"JL23K5C4KYG4AF7K","created_at":"2026-07-05T11:54:54Z"},{"alias_kind":"pith_short_8","alias_value":"JL23K5C4","created_at":"2026-07-05T11:54:54Z"}],"graph_snapshots":[{"event_id":"sha256:5c0d85c4d817edd8dfea035fe9d1895ab7ace1b340b13487efcce2ee8db5ec4a","target":"graph","created_at":"2026-07-05T11:54:54Z","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/2508.11800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing language models in verifiable domains with stochastic outcomes, like scientific experiments. Through applications to synthetic data and real-world biological experiments, we demonstrate that Group Relative Policy Optimization (GRPO) induces overconfident probability predictions for binary stochastic outcomes, while Proximal Policy Optimization (PPO) and REINFORCE","authors_text":"Jure Leskovec, Michael Bereket","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T20:50:53Z","title":"Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11800","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:a6068cf3aee07b04df9c974ffd58286e55d5c5af029d9b439e965bc5ba01e5d7","target":"record","created_at":"2026-07-05T11:54:54Z","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":"c3b47b74bad2ee05b1732e7d303acded8de2e0849be8931b5a445d39d162695a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T20:50:53Z","title_canon_sha256":"83f20d1a2a7dd4a8c42dd62ef166e8c3217539be6ee78c5edff779e19acf8617"},"schema_version":"1.0","source":{"id":"2508.11800","kind":"arxiv","version":1}},"canonical_sha256":"4af5b5745c560dc017eaeeec94d018dd270e2ea8d2e0779d735d86643cd35e50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4af5b5745c560dc017eaeeec94d018dd270e2ea8d2e0779d735d86643cd35e50","first_computed_at":"2026-07-05T11:54:54.671739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:54.671739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7RS7vFjCBrRBrhL6POCoFLpjx4OUBQRaRDwRph6njSZPAw3aECn1rXpxYttjkCdpFi5WX+lT2lh0ZKWwPr+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:54.672248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6068cf3aee07b04df9c974ffd58286e55d5c5af029d9b439e965bc5ba01e5d7","sha256:5c0d85c4d817edd8dfea035fe9d1895ab7ace1b340b13487efcce2ee8db5ec4a"],"state_sha256":"003f150bf7eab84308f78e490b3e6265c7fd80d20d93ad41e2ad453dcdf4473b"}