{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:656HFSJ7THBWN3GHJHQWT5MVW4","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":"f9faed489ee62df1f70bcddbdfc52e7ef2158ef624a4de7315146d9f62438821","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:02:26Z","title_canon_sha256":"afeff60a69ac3c19b443b337d212e619d96f8c98fbdb084a360eadf59537ebc1"},"schema_version":"1.0","source":{"id":"2608.03467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03467","created_at":"2026-08-05T01:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03467v1","created_at":"2026-08-05T01:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03467","created_at":"2026-08-05T01:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"656HFSJ7THBW","created_at":"2026-08-05T01:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"656HFSJ7THBWN3GH","created_at":"2026-08-05T01:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"656HFSJ7","created_at":"2026-08-05T01:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:fab1bf5b84b5ed4584f345fff2ff6c077d2b0cb34cddcc5742f430e621ee56da","target":"graph","created_at":"2026-08-05T01:35:54Z","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/2608.03467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) com- monly optimizes each correct completion as an independent learning signal. In GRPO, this completion-level uniformity creates structure-level skew: recurring correct solution forms accumulate positive coefficient mass in proportion to how often they are sampled, while rare forms receive limited credit. We formalize this behavior as multiplicity-induced structure-level credit concentration and introduce a partition- conditioned rule that redistributes positive advantages accord- ing to cluster rarity. Cue-GRPO instantiates this rule with","authors_text":"Fangjiong Chen, Miaowen Wen, Zhe Cao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:02:26Z","title":"When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03467","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:ca4551c13317dca43df9d1692491a9c8e54d19cfdcbc64a831e5afbc2e1b9953","target":"record","created_at":"2026-08-05T01:35:54Z","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":"f9faed489ee62df1f70bcddbdfc52e7ef2158ef624a4de7315146d9f62438821","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:02:26Z","title_canon_sha256":"afeff60a69ac3c19b443b337d212e619d96f8c98fbdb084a360eadf59537ebc1"},"schema_version":"1.0","source":{"id":"2608.03467","kind":"arxiv","version":1}},"canonical_sha256":"f77c72c93f99c366ecc749e169f595b737ce1dd4db3fdbb34a36bf90d11b6874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f77c72c93f99c366ecc749e169f595b737ce1dd4db3fdbb34a36bf90d11b6874","first_computed_at":"2026-08-05T01:35:54.692926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:54.692926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JeLJY4h+5ee36VvrLrtW1JTvwJYwj9LdQSQ42JfS4JhOCs/N06A0cZOnZbmP8mzmD/Z8VvPnocQHsBM8GmY1Dw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:54.694803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca4551c13317dca43df9d1692491a9c8e54d19cfdcbc64a831e5afbc2e1b9953","sha256:fab1bf5b84b5ed4584f345fff2ff6c077d2b0cb34cddcc5742f430e621ee56da"],"state_sha256":"e999b549d574ee64cb66b13c8ac732ba0a5b70261f84073483da1597854c1ac5"}