{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BVSY6CPCP44NATVJ3SJROMETWK","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":"be2e9d7010393060dada23af3ddec99aa7b898f6691973ad09370826efd3a09f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T12:45:55Z","title_canon_sha256":"62078b236cb84ebb7781832b7d95203310fe3583925777155166de5d00de1941"},"schema_version":"1.0","source":{"id":"2607.26862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26862","created_at":"2026-07-30T01:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26862v1","created_at":"2026-07-30T01:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26862","created_at":"2026-07-30T01:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"BVSY6CPCP44N","created_at":"2026-07-30T01:22:33Z"},{"alias_kind":"pith_short_16","alias_value":"BVSY6CPCP44NATVJ","created_at":"2026-07-30T01:22:33Z"},{"alias_kind":"pith_short_8","alias_value":"BVSY6CPC","created_at":"2026-07-30T01:22:33Z"}],"graph_snapshots":[{"event_id":"sha256:b717530b3f255f05581600f5992acd04a7ff65070d57e1c2d4c313887d08a0fb","target":"graph","created_at":"2026-07-30T01:22:33Z","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/2607.26862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability. We trace this concentration to two mechanisms in the GRPO update. At the response level, high-probability responses dominate the group gradient through repeated ","authors_text":"Junoh Park, Junseo Hwang, Taesup Kim, Wonguk Cho","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T12:45:55Z","title":"ReCo: Reweighting GRPO Against Distributional Concentration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26862","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":"sha256:301bf1a44adc6664fde4d0b2a77928d55a9b99d2089bc64e2ebb3d8e1072c0bb","target":"record","created_at":"2026-07-30T01:22:33Z","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":"be2e9d7010393060dada23af3ddec99aa7b898f6691973ad09370826efd3a09f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T12:45:55Z","title_canon_sha256":"62078b236cb84ebb7781832b7d95203310fe3583925777155166de5d00de1941"},"schema_version":"1.0","source":{"id":"2607.26862","kind":"arxiv","version":1}},"canonical_sha256":"0d658f09e27f38d04ea9dc93173093b2b1a97b7d88eb74c60af565f0860b7645","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d658f09e27f38d04ea9dc93173093b2b1a97b7d88eb74c60af565f0860b7645","first_computed_at":"2026-07-30T01:22:33.501976Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:22:33.501976Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:301bf1a44adc6664fde4d0b2a77928d55a9b99d2089bc64e2ebb3d8e1072c0bb","sha256:b717530b3f255f05581600f5992acd04a7ff65070d57e1c2d4c313887d08a0fb"],"state_sha256":"28c64e54c86e22c22a26ae72a9471eba44635ee8a51503ab0789d9c589bb0e1f"}