{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VELLFZZDUPFLLWUU3E2HJM7IX2","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":"5765a44474f9ff641dd167e746f4b73ac763141c7308f6bca44cd56b5ccfb13a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T10:51:58Z","title_canon_sha256":"f0793e2cebdc249d939d01035265c6c3f89faba999e23dfe2bfd2a808af770c8"},"schema_version":"1.0","source":{"id":"2602.08499","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08499","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08499v2","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08499","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"VELLFZZDUPFL","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"VELLFZZDUPFLLWUU","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"VELLFZZD","created_at":"2026-05-26T02:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:7ae44a6157bea741978f25738a73ebb84cd149e5e07686c1ef6321eced4d7ecc","target":"graph","created_at":"2026-05-26T02:04:05Z","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/2602.08499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a single use. This leads to noisy supervision, poor sample efficiency, and suboptimal policy updates. We address these issues by formulating rollout scheduling in RLVR as a contextual bandit problem and proposing a unified neural scheduli","authors_text":"Deqing Wang, Fuzhen Zhuang, Guojun Yin, Jiajun Chai, Wei Lin, Xiaodong Lu, Xiaohan Wang, Yikun Ban, Yu Luo, Zhijun Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T10:51:58Z","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08499","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:cb81ea636cc1d81d3b652985c9a591e126aeb2ecc3eef3d2a9ca66107ef84138","target":"record","created_at":"2026-05-26T02:04:05Z","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":"5765a44474f9ff641dd167e746f4b73ac763141c7308f6bca44cd56b5ccfb13a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T10:51:58Z","title_canon_sha256":"f0793e2cebdc249d939d01035265c6c3f89faba999e23dfe2bfd2a808af770c8"},"schema_version":"1.0","source":{"id":"2602.08499","kind":"arxiv","version":2}},"canonical_sha256":"a916b2e723a3cab5da94d93474b3e8bea518cfd8f96377baf134d420c84b80fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a916b2e723a3cab5da94d93474b3e8bea518cfd8f96377baf134d420c84b80fd","first_computed_at":"2026-05-26T02:04:05.822046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:05.822046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G6f4RAa12SMMEmbknMEfqlBBVjVIPFa15TzQLAo8/OyEbncPCzBIe0r4vIKjH20DG9eHhASA/Vd917JX0iuOBA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:05.823072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08499","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb81ea636cc1d81d3b652985c9a591e126aeb2ecc3eef3d2a9ca66107ef84138","sha256:7ae44a6157bea741978f25738a73ebb84cd149e5e07686c1ef6321eced4d7ecc"],"state_sha256":"fb5e36c9c5ffe44840df8d5168a773a50a8aa2c32f0c6f8d4dcfe7f1879bb44f"}