{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5DGV25FM5YI3HFE6MGLUINXHTS","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":"2383eeed4be5b7d8b47bc6aede7d5c57292971d96b2c69131d8c87b761d70e60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:25:56Z","title_canon_sha256":"77ebb098cfab7a08a4566e408a59ea6945e4319467d22915ec429b256c28a81c"},"schema_version":"1.0","source":{"id":"2605.30789","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30789","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30789v1","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30789","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"5DGV25FM5YI3","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"5DGV25FM5YI3HFE6","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"5DGV25FM","created_at":"2026-06-01T01:03:16Z"}],"graph_snapshots":[{"event_id":"sha256:aa8b9784c783666a96c6475972e483d23d03c57f0fb74a7878f2fd0897d9677b","target":"graph","created_at":"2026-06-01T01:03:16Z","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/2605.30789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies primarily increase diversity by injecting more token-level randomness, which may introduce step-wise noise and lead to incoherent trajectories. We uncover that smaller models within the same model family inherently exhibit higher policy-level diversity, indicated by their superior pass@k relative to larger counterparts as sample counts increase. Unlike token-level noise, this diversity is temporally correlated, preserves","authors_text":"Chufan Shi, Dingdong Wang, Junjie Wang, Ruihang Chu, Tianhe Wu, Yiming Ren, Yiran Xu, Yujiu Yang, Yukang Chen, Yu Qiao, Zicheng Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:25:56Z","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30789","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:e7c92b7d741ac522955d9e472451cb1f3d967242e7cc87a43a1df7af3a95bbc8","target":"record","created_at":"2026-06-01T01:03:16Z","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":"2383eeed4be5b7d8b47bc6aede7d5c57292971d96b2c69131d8c87b761d70e60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T03:25:56Z","title_canon_sha256":"77ebb098cfab7a08a4566e408a59ea6945e4319467d22915ec429b256c28a81c"},"schema_version":"1.0","source":{"id":"2605.30789","kind":"arxiv","version":1}},"canonical_sha256":"e8cd5d74acee11b3949e61974436e79ca6efd4823d713f022a21b1ae97bd01eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8cd5d74acee11b3949e61974436e79ca6efd4823d713f022a21b1ae97bd01eb","first_computed_at":"2026-06-01T01:03:16.750284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:16.750284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"deefPeqgXB81TWpPoewjvsNxx7YYGovWSBb/coPBzc/biwn2WGDsCTBVl2y4Q6R0Jni7fpwKwEGevEtVkfcUBg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:16.750989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30789","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c92b7d741ac522955d9e472451cb1f3d967242e7cc87a43a1df7af3a95bbc8","sha256:aa8b9784c783666a96c6475972e483d23d03c57f0fb74a7878f2fd0897d9677b"],"state_sha256":"6b567e5ea80784d6cbbcbdc74be9cff033a943fa81508103be558ccbddd6d9c3"}