{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GFZXOLDPMTM5K66QYH7ZODT355","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":"5851894f5dbd5f5170ad7c783451938a566e9ee2542bd22be737bec05ffe1516","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:56:44Z","title_canon_sha256":"50b14707283d27f30d99764afcacfd6216452044f84fffe573ff13caf6e51258"},"schema_version":"1.0","source":{"id":"2510.00915","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00915","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00915v4","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00915","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"GFZXOLDPMTM5","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"GFZXOLDPMTM5K66Q","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"GFZXOLDP","created_at":"2026-05-25T02:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:dbc12a266ec38f73f8f6b57559c888d25a1be716cc86149042bc0ec18e48fc8e","target":"graph","created_at":"2026-05-25T02:01:07Z","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/2510.00915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\\{0,1\\}$, but imperfect verifiers inevitably introduce \\emph{false negatives} (rejecting correct answers) and \\emph{false positives} (accepting incorrect ones). We formalize verifier unreliability as a stochastic reward channel with asymmetric noise rates $\\rho_0$ and $\\rho_1$ -- the FP rate and the FN rate, respectively. From this abstraction we derive two lightweight corrections: (i) a \\emph{backward} correction that","authors_text":"Feng Liu, Gang Niu, Masashi Sugiyama, Tongliang Liu, Wei Wang, Xin-Qiang Cai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:56:44Z","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00915","kind":"arxiv","version":4},"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":"sha256:8144ec9994db9d912d47b5d59aac0627d51ed1c358d2040173c57d2a4bc1d820","target":"record","created_at":"2026-05-25T02:01:07Z","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":"5851894f5dbd5f5170ad7c783451938a566e9ee2542bd22be737bec05ffe1516","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T13:56:44Z","title_canon_sha256":"50b14707283d27f30d99764afcacfd6216452044f84fffe573ff13caf6e51258"},"schema_version":"1.0","source":{"id":"2510.00915","kind":"arxiv","version":4}},"canonical_sha256":"3173772c6f64d9d57bd0c1ff970e7bef721a95c85831f9e21f076b3d86b3744c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3173772c6f64d9d57bd0c1ff970e7bef721a95c85831f9e21f076b3d86b3744c","first_computed_at":"2026-05-25T02:01:07.698940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:07.698940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MrKaImT3C48v2U1ia59M4nsizwLm5uboRxC/LGoF1x6LvRiTtJ3KK2451UgLAD5s5WilvvGKi6opPxTVe35bBQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:07.699956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.00915","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8144ec9994db9d912d47b5d59aac0627d51ed1c358d2040173c57d2a4bc1d820","sha256:dbc12a266ec38f73f8f6b57559c888d25a1be716cc86149042bc0ec18e48fc8e"],"state_sha256":"843fd33d35dd8de1013d37d2d60ea8a7faa594e0cf46af1825b1e8651d851081"}