{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UU7TUH2FBN2CH6FTL75YUNHXKE","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":"4a4f575b64c2f70243b5a7c4c9ed2fc928af64c324303a3120c8f9bb6d7101f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T04:41:20Z","title_canon_sha256":"ee3f2c847652c588077e7e48f67a0459afa5f0ed7ef9d8d91185b38dc83dd71b"},"schema_version":"1.0","source":{"id":"2608.03119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03119","created_at":"2026-08-05T00:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03119v1","created_at":"2026-08-05T00:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03119","created_at":"2026-08-05T00:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"UU7TUH2FBN2C","created_at":"2026-08-05T00:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"UU7TUH2FBN2CH6FT","created_at":"2026-08-05T00:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"UU7TUH2F","created_at":"2026-08-05T00:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:e1f4e989cec2190078db55efcb4fdc056938a037b0cc306a5d8bf9dfa46a5de3","target":"graph","created_at":"2026-08-05T00:45:43Z","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/2608.03119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability. Voting-based label-free RLVR replace gold supervision with answer-level consensus from model samples. However, collapse arises when the same answer-level signal is used both to estimate rewards and to drive token-level policy optimization, encouraging the model to directly reinforce answer tokens rather than improve reasoning. We propose OM-GRPO, a label-free RLVR framework that decouples reward estimation from policy optimization. OM-GRPO masks ","authors_text":"Biao Fu, Liang Zhang, Xiaodong Shi, Yidong Chen, Yongshi Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T04:41:20Z","title":"Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03119","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:d7bd3225ef4523cb4228ba633037e81be32f4177c9d990bdf90606989dccf62b","target":"record","created_at":"2026-08-05T00:45:43Z","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":"4a4f575b64c2f70243b5a7c4c9ed2fc928af64c324303a3120c8f9bb6d7101f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T04:41:20Z","title_canon_sha256":"ee3f2c847652c588077e7e48f67a0459afa5f0ed7ef9d8d91185b38dc83dd71b"},"schema_version":"1.0","source":{"id":"2608.03119","kind":"arxiv","version":1}},"canonical_sha256":"a53f3a1f450b7423f8b35ffb8a34f75111787c8c0754ed456340c8e6a36867a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a53f3a1f450b7423f8b35ffb8a34f75111787c8c0754ed456340c8e6a36867a4","first_computed_at":"2026-08-05T00:45:43.722287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:45:43.722287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fgM19WapQnkdOY4xqXTRR0QJ1mW82Gk/9pCpAunFhwFSPMHYtmrPAGszAtGRXYiZl+9GyJ/DMX/v7WsDqvPiAQ==","signature_status":"signed_v1","signed_at":"2026-08-05T00:45:43.724654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7bd3225ef4523cb4228ba633037e81be32f4177c9d990bdf90606989dccf62b","sha256:e1f4e989cec2190078db55efcb4fdc056938a037b0cc306a5d8bf9dfa46a5de3"],"state_sha256":"72757f3ec2fa375f182159956cb30d6a342a9889136bacb390aef983b20704cc"}