{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OEOH5MG6DJODA2K45PBHR3HXE6","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":"fa2bc6130e3f106ebda35cda844334556bddd6baa39ab5971d1b4736e4f5f948","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T15:34:47Z","title_canon_sha256":"9ad8bb18d9b51d321fd2f9abbafaac22075102ef8aaf1102cd36cc9257369a24"},"schema_version":"1.0","source":{"id":"2508.10751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10751","created_at":"2026-07-05T11:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10751v1","created_at":"2026-07-05T11:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10751","created_at":"2026-07-05T11:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"OEOH5MG6DJOD","created_at":"2026-07-05T11:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"OEOH5MG6DJODA2K4","created_at":"2026-07-05T11:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"OEOH5MG6","created_at":"2026-07-05T11:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:035534422f421e20ef55b97c62907721c911e9c83361d3494ff0f55ba949ab68","target":"graph","created_at":"2026-07-05T11:54:02Z","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/2508.10751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies to prefer conservative actions, converging to a local optimum. Identifying an appropriate reward metric is therefore crucial. Regarding the prior work, although Pass@k has been used in evaluation, its connection to LLM exploration ability in RLVR remains largely overlooked. To investigate this, we first use Pass@k as the reward to train the policy model (i.e., $\\textbf{Pass@k Training}$), and observe the improvement","authors_text":"Guang Shi, Qinghao Ye, Wayne Xin Zhao, Xiaobo Qin, Youbin Wu, Yue Ling, Zhipeng Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T15:34:47Z","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10751","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":"sha256:8265ac51c1b67383e6ebb80964b15b6762f336cd483cea90f88074d7cec1e010","target":"record","created_at":"2026-07-05T11:54:02Z","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":"fa2bc6130e3f106ebda35cda844334556bddd6baa39ab5971d1b4736e4f5f948","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T15:34:47Z","title_canon_sha256":"9ad8bb18d9b51d321fd2f9abbafaac22075102ef8aaf1102cd36cc9257369a24"},"schema_version":"1.0","source":{"id":"2508.10751","kind":"arxiv","version":1}},"canonical_sha256":"711c7eb0de1a5c30695cebc278ecf7278ce183451ed9b91ea0cde980ff548bb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"711c7eb0de1a5c30695cebc278ecf7278ce183451ed9b91ea0cde980ff548bb4","first_computed_at":"2026-07-05T11:54:02.004742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:02.004742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OWE6E7UAWmhtvrqLbcxiFMUZodfjLgWcYjawr00s+m2Im8QhN6krVaAxFHtKl1OtKKxSiEl8olv9LyiSxTRbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:02.005090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8265ac51c1b67383e6ebb80964b15b6762f336cd483cea90f88074d7cec1e010","sha256:035534422f421e20ef55b97c62907721c911e9c83361d3494ff0f55ba949ab68"],"state_sha256":"13cb5c2dae1f90c4d90e3d02d36fa49381e6755a7b5ff92c1fcff8ac9086766f"}