{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5RFNVCMEQFLH4FFSJVUHGGF7CB","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":"2aad8c27a3f0365f3dc502300f031fbc38758dcc37081fa18c300d1e85824e3e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T10:23:24Z","title_canon_sha256":"2b4e74f76157aed683e49749cada258f35f00a6f8b4c81c2228bee69710d5e44"},"schema_version":"1.0","source":{"id":"2606.08088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08088","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08088v1","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08088","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"5RFNVCMEQFLH","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"5RFNVCMEQFLH4FFS","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"5RFNVCME","created_at":"2026-06-09T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:3682589574f9bcc16636764108fcdbd57004f1c9fd3c4c2080551367784addd4","target":"graph","created_at":"2026-06-09T01:05:25Z","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/2606.08088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models (LLMs), yet it remains limited by sparse binary rewards and its ignorance of model-internal uncertainty. In this paper, we propose ConSteer-RL, a simple yet effective framework that integrates token-level confidence signals derived from model log-probabilities into RLVR training. Specifically, building upon the Group Relative Policy Optimization (GRPO) framework, we construct a confidence-aware reward by aggregating per-token probabilities into","authors_text":"Badong Chen, Chenxi Liu, Jing Yang, Qing Miao, Shaoyi Du, Yiming Zhao, Yuehai Chen, Yuewen Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T10:23:24Z","title":"ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08088","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":"sha256:8f03eeb7b5795ccbb1907663b016e5139074fc12bae6112959b2cb1930f5b22f","target":"record","created_at":"2026-06-09T01:05:25Z","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":"2aad8c27a3f0365f3dc502300f031fbc38758dcc37081fa18c300d1e85824e3e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T10:23:24Z","title_canon_sha256":"2b4e74f76157aed683e49749cada258f35f00a6f8b4c81c2228bee69710d5e44"},"schema_version":"1.0","source":{"id":"2606.08088","kind":"arxiv","version":1}},"canonical_sha256":"ec4ada898481567e14b24d687318bf106dfe942e2baa5c2029ff1418e71204ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4ada898481567e14b24d687318bf106dfe942e2baa5c2029ff1418e71204ad","first_computed_at":"2026-06-09T01:05:25.928074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:25.928074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x4FCN8UJdv5OO1g4RXMSpdnTiq0Smfuc2IoiQTSW/Tyku0aSX+Uz2bcNuHKK3SWegqNEJtWmoPwTzujsJVPhDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:25.928706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f03eeb7b5795ccbb1907663b016e5139074fc12bae6112959b2cb1930f5b22f","sha256:3682589574f9bcc16636764108fcdbd57004f1c9fd3c4c2080551367784addd4"],"state_sha256":"644700cfba92501c2d4886be0bcdc24b506125aee59ee2e5d46f5014adb7707a"}