{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WED7MUTHUDSYV6TWDILTJCVYJD","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":"47078ade56c60de162c8d6b3f518e18665420a3beef43de01f656ef117e8757a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:11:09Z","title_canon_sha256":"7349ce5e641e917240f8e83664094e2a33b48019268787aa533b66eb6818de43"},"schema_version":"1.0","source":{"id":"2606.03608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03608","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03608v1","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03608","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"WED7MUTHUDSY","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"WED7MUTHUDSYV6TW","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"WED7MUTH","created_at":"2026-06-03T01:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:c4f7f27f2315ce4c3efa3896f230fe9730439e1792b34a233f6792115cb86ee7","target":"graph","created_at":"2026-06-03T01:06:02Z","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/2606.03608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner. Despite existing studies focusing on Pass@1 performance, optimizing Pass@k remains under-explored yet critical in label-free settings, which measures generation coverage for sustained exploration. Optimizing Pass@k in label-free setting is highly non-trivial, as directly applying the Pass@k advantage designs effective for RLVR yields unsatisfactory performance. Through in-depth empirical analysis, we discover the root cau","authors_text":"Dan Li, Jiahui Li, Jianfeng Shan, Jian Lou, See-kiong Ng, Shunyu Wu, Wenjie Feng, Wenpei Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:11:09Z","title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03608","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":"sha256:471beaf6c9efeb194cae467d9d6a4f0b3ece1ea5e06ea874cbf09ae538437924","target":"record","created_at":"2026-06-03T01:06:02Z","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":"47078ade56c60de162c8d6b3f518e18665420a3beef43de01f656ef117e8757a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T13:11:09Z","title_canon_sha256":"7349ce5e641e917240f8e83664094e2a33b48019268787aa533b66eb6818de43"},"schema_version":"1.0","source":{"id":"2606.03608","kind":"arxiv","version":1}},"canonical_sha256":"b107f65267a0e58afa761a17348ab848e2364290295803ce0c855afd5ab602be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b107f65267a0e58afa761a17348ab848e2364290295803ce0c855afd5ab602be","first_computed_at":"2026-06-03T01:06:02.255721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:02.255721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B54R3Vw3/EOGZpdq0dXMvQLTS9j+lPDT9rop7HMc95tmMAvJnvXXz+7XTGykIpyPEkSGI/dLT3PR8+H14O4eDA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:02.256199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:471beaf6c9efeb194cae467d9d6a4f0b3ece1ea5e06ea874cbf09ae538437924","sha256:c4f7f27f2315ce4c3efa3896f230fe9730439e1792b34a233f6792115cb86ee7"],"state_sha256":"a18b9015e1b09a234e6820e58b7b12966aa3990759e82f05f319b4ecc86a2f8a"}