{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FTTOUIFIDTXADP7WFWR6OTOZTY","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":"55d1db8bdd43c2f3b2bcd4ee27c40a524922b25e9c1bebbd6f1b3bc827e0ba26","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T08:52:31Z","title_canon_sha256":"bbe4ef8d32286d5012ed0353f645fa6d9d17eafaa216bde6b8fed244bcda1e98"},"schema_version":"1.0","source":{"id":"2605.17333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17333","created_at":"2026-05-20T00:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17333v1","created_at":"2026-05-20T00:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17333","created_at":"2026-05-20T00:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"FTTOUIFIDTXA","created_at":"2026-05-20T00:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"FTTOUIFIDTXADP7W","created_at":"2026-05-20T00:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"FTTOUIFI","created_at":"2026-05-20T00:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:d94004dc84dca20263367a75cbcf30739160c0fec2b6cd8d3c28b8289e126fd5","target":"graph","created_at":"2026-05-20T00:03:52Z","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":"claim_evidence","ran_at":"2026-05-19T21:41:57.807902Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.742052Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17333/integrity.json","findings":[],"snapshot_sha256":"afab0c06e36f2f84ce41f4c1b5f4db8b73c075f6e31d18962df2fc36beb5c93c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness, yet the collective structure of the group output, specifically the distribution of errors, is largely discarded. We identify this as a missed opportunity: empirical analysis reveals that error diversity within a group is a strong predictor of training success, with problems eliciting diverse wrong answers benefiting substantially more from RLVR than those producing homogeneous failures. Motivated by this observation, we propose Error ","authors_text":"Jiaqi Wang, Nan Duan, Shuai Dong, Tong Yang, Weichu Xie, Wenpu Liu, Wenqi Shao, Xiaoying Zhang, Yongfu Zhu, Yuqi Xu, Ziyue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T08:52:31Z","title":"Leveraging Error Diversity in Group Rollouts for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17333","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":"sha256:9ba1b30b72341dcc67c250d8ef06cde94240c3398159f768a7d45b3a7032f4a4","target":"record","created_at":"2026-05-20T00:03:52Z","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":"55d1db8bdd43c2f3b2bcd4ee27c40a524922b25e9c1bebbd6f1b3bc827e0ba26","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T08:52:31Z","title_canon_sha256":"bbe4ef8d32286d5012ed0353f645fa6d9d17eafaa216bde6b8fed244bcda1e98"},"schema_version":"1.0","source":{"id":"2605.17333","kind":"arxiv","version":1}},"canonical_sha256":"2ce6ea20a81cee01bff62da3e74dd99e1445393c014cc196a053d24869462586","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ce6ea20a81cee01bff62da3e74dd99e1445393c014cc196a053d24869462586","first_computed_at":"2026-05-20T00:03:52.639460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:52.639460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qq/7Eo9kYAeldmODwdxUKxicVEdgUbgY6E7YJUMJAQkUERszCsIdO317bWnpplh/WPXiZWlWzLnFoC+WrLyoDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:52.640297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ba1b30b72341dcc67c250d8ef06cde94240c3398159f768a7d45b3a7032f4a4","sha256:d94004dc84dca20263367a75cbcf30739160c0fec2b6cd8d3c28b8289e126fd5"],"state_sha256":"a80e9e30e8982afbcadaeebe52035b339e8c93b57e121052eb1149dfd412a432"}