{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XP2WRVK3EV7WE6Z6Y4JGD5LVB7","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":"d537f8ad941455a5b4f8b25047096297e02427de595c74c3e678d857de828d83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T08:54:37Z","title_canon_sha256":"85cb99a8d1a014216a2a098c6ae43588ebdcc8c2583c7c8bd5ce40df35502a4b"},"schema_version":"1.0","source":{"id":"2605.23384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23384","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23384v1","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23384","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"XP2WRVK3EV7W","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"XP2WRVK3EV7WE6Z6","created_at":"2026-05-25T02:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"XP2WRVK3","created_at":"2026-05-25T02:01:51Z"}],"graph_snapshots":[{"event_id":"sha256:659ae829c305d823eac784d2b14e71baec2e26bb41fb150106c1e59587de6701","target":"graph","created_at":"2026-05-25T02:01:51Z","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/2605.23384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or ground-truth answers, but provides limited guidance for intermediate reasoning behaviors. (2) Rubrics-as-reward (RaR) goes beyond final-answer checking by using natural-language rubrics to assess reasoning quality and task compliance, but often requires instance-specific rubrics and substantial design effort. To address these issues, we introduce Metacogniti","authors_text":"Beier Zhu, Chaochao Lu, Hanwang Zhang, Lei Xu, Shengjie Zhao, Sirui Chen, Yutian Chen, Yu Wang, Yuying Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T08:54:37Z","title":"Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23384","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":"sha256:7745365997042a58ad349681fc793a37748b9eadcd88de747fa50799a92b77f7","target":"record","created_at":"2026-05-25T02:01:51Z","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":"d537f8ad941455a5b4f8b25047096297e02427de595c74c3e678d857de828d83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T08:54:37Z","title_canon_sha256":"85cb99a8d1a014216a2a098c6ae43588ebdcc8c2583c7c8bd5ce40df35502a4b"},"schema_version":"1.0","source":{"id":"2605.23384","kind":"arxiv","version":1}},"canonical_sha256":"bbf568d55b257f627b3ec71261f5750fccac31d3616642b70944a08d593c88de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbf568d55b257f627b3ec71261f5750fccac31d3616642b70944a08d593c88de","first_computed_at":"2026-05-25T02:01:51.806019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:51.806019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HFnjlJT1HcN5wS9I8+njEMCNhK5efmV8OVrLMfJBqa0q1v9ltQj19v+hBFNzEXem2oK/+OekyFz/EF1dOxSjBg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:51.806629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7745365997042a58ad349681fc793a37748b9eadcd88de747fa50799a92b77f7","sha256:659ae829c305d823eac784d2b14e71baec2e26bb41fb150106c1e59587de6701"],"state_sha256":"7fb2ddcb905fe715dfeecb063f1fe2f05f4371cb512827fa4cabf2fc2e7c6e39"}