{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6LX4WER7LTSW7XYJTTXEZQNZ6C","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":"771d361f9f7219be9e335f4f3d626e43c2669f8ef7518723eef404568343c4f6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T08:22:59Z","title_canon_sha256":"6b16530f05d5f412008cd3f0469503082c10e9549bd0354dc8df9b3a00572d37"},"schema_version":"1.0","source":{"id":"2605.15726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15726","created_at":"2026-05-20T00:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15726v1","created_at":"2026-05-20T00:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15726","created_at":"2026-05-20T00:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"6LX4WER7LTSW","created_at":"2026-05-20T00:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"6LX4WER7LTSW7XYJ","created_at":"2026-05-20T00:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"6LX4WER7","created_at":"2026-05-20T00:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:b81e9aadb62461a4e17f7164ef10aa3ad8dcb3506e2f28c571ebb2aa40ac4b75","target":"graph","created_at":"2026-05-20T00:01:15Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:25.151602Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.999339Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15726/integrity.json","findings":[],"snapshot_sha256":"b05bea29b83e6ea2ecef68eb1029c8ae363d55665da39e4a858bb46f083653bf","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally expensive, and existing approaches that modify the optimization objective provide limited control over what is explored. In this work, we propose NudgeRL, a framework for structured and diversity-drive","authors_text":"Chanuk Lee, Minki Kang, Sangwoo Park, Sung Ju Hwang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T08:22:59Z","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15726","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":"sha256:65be93885cec5f3a2841a7ba7e66b6dbe8cd9f8087188bbcab9d9dd6df1c4b0a","target":"record","created_at":"2026-05-20T00:01:15Z","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":"771d361f9f7219be9e335f4f3d626e43c2669f8ef7518723eef404568343c4f6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T08:22:59Z","title_canon_sha256":"6b16530f05d5f412008cd3f0469503082c10e9549bd0354dc8df9b3a00572d37"},"schema_version":"1.0","source":{"id":"2605.15726","kind":"arxiv","version":1}},"canonical_sha256":"f2efcb123f5ce56fdf099cee4cc1b9f0b4ed5bb1f92951cbced20a277d54de63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2efcb123f5ce56fdf099cee4cc1b9f0b4ed5bb1f92951cbced20a277d54de63","first_computed_at":"2026-05-20T00:01:15.092642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:15.092642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9n6O5QhdLn/l/x7at9sBMBR74VHrG07QxGPzve1t0d/eWV1NuHj4GTI6EOS4xBCkk63NIQ41xu9nnfL2lnbrDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:15.093420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65be93885cec5f3a2841a7ba7e66b6dbe8cd9f8087188bbcab9d9dd6df1c4b0a","sha256:b81e9aadb62461a4e17f7164ef10aa3ad8dcb3506e2f28c571ebb2aa40ac4b75"],"state_sha256":"2162567227bf6761b984881c3769fb73bb0519554837d46ac0be7f83345facea"}