{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3JQDU2X5BXM2OCQ2IQ63GQDH3S","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":"ea44a5c1a4dd15c0dfebc002406976c960d6bc868f1ae9e9290aed62138cc3fe","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-10T03:38:17Z","title_canon_sha256":"6fd71bac58d0c20a2db112d9f81d60c503419a619395dc081c5980598154ec73"},"schema_version":"1.0","source":{"id":"2510.08977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.08977","created_at":"2026-06-03T01:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2510.08977v2","created_at":"2026-06-03T01:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08977","created_at":"2026-06-03T01:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"3JQDU2X5BXM2","created_at":"2026-06-03T01:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"3JQDU2X5BXM2OCQ2","created_at":"2026-06-03T01:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"3JQDU2X5","created_at":"2026-06-03T01:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:7dc2ddaeb5d6c8227a535319b901f358c05618ad15580b90d9a7d4b3e4fe3209","target":"graph","created_at":"2026-06-03T01:05:45Z","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/2510.08977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforcement learning with intrinsic rewards (RLIR) offers a scalable alternative via self-rewarding, yet often suffers from instability and inferior performance. We trace this gap to a systemic bias in confidence-coupled self-rewarding: the model tends to over-reward high-confidence mistakes, forming a self-confirming loop. We quantify this feedback-loop bias with three metrics: reward noise magnitude (rho_noise), policy-re","authors_text":"Boyuan Pan, Chuyi Tan, Jiayi Shi, Ji Zhang, Kan Li, Peiwen Yuan, Shaoxiong Feng, Xinglin Wang, Yao Hu, Yiwei Li, Yueqi Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-10T03:38:17Z","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08977","kind":"arxiv","version":2},"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:f60814f8786e37e8d58fc7baa7a643ac8ac67a32c64ae8a2ee674595946175b3","target":"record","created_at":"2026-06-03T01:05:45Z","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":"ea44a5c1a4dd15c0dfebc002406976c960d6bc868f1ae9e9290aed62138cc3fe","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-10T03:38:17Z","title_canon_sha256":"6fd71bac58d0c20a2db112d9f81d60c503419a619395dc081c5980598154ec73"},"schema_version":"1.0","source":{"id":"2510.08977","kind":"arxiv","version":2}},"canonical_sha256":"da603a6afd0dd9a70a1a443db34067dc9d1c1b34f13373f49a96d6046b7c2b68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da603a6afd0dd9a70a1a443db34067dc9d1c1b34f13373f49a96d6046b7c2b68","first_computed_at":"2026-06-03T01:05:45.626366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:45.626366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d969Dnwt21SklBEkoXZrFQoKQyFWE1sU46HHtSypvLqV2VyimCiyGfof4V99q0h5gNWMx4JBHYnEwI8DQoEHAg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:45.626867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.08977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f60814f8786e37e8d58fc7baa7a643ac8ac67a32c64ae8a2ee674595946175b3","sha256:7dc2ddaeb5d6c8227a535319b901f358c05618ad15580b90d9a7d4b3e4fe3209"],"state_sha256":"361d9fd45c57ad8553ce1ab8caab0bc151964f1a6b3a8722670a48884a015a75"}