{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:656HFSJ7THBWN3GHJHQWT5MVW4","short_pith_number":"pith:656HFSJ7","schema_version":"1.0","canonical_sha256":"f77c72c93f99c366ecc749e169f595b737ce1dd4db3fdbb34a36bf90d11b6874","source":{"kind":"arxiv","id":"2608.03467","version":1},"attestation_state":"computed","paper":{"title":"When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fangjiong Chen, Miaowen Wen, Zhe Cao","submitted_at":"2026-08-04T11:02:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T11:02:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"afeff60a69ac3c19b443b337d212e619d96f8c98fbdb084a360eadf59537ebc1","abstract_canon_sha256":"f9faed489ee62df1f70bcddbdfc52e7ef2158ef624a4de7315146d9f62438821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:54.694803Z","signature_b64":"JeLJY4h+5ee36VvrLrtW1JTvwJYwj9LdQSQ42JfS4JhOCs/N06A0cZOnZbmP8mzmD/Z8VvPnocQHsBM8GmY1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f77c72c93f99c366ecc749e169f595b737ce1dd4db3fdbb34a36bf90d11b6874","last_reissued_at":"2026-08-05T01:35:54.692926Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:54.692926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fangjiong Chen, Miaowen Wen, Zhe Cao","submitted_at":"2026-08-04T11:02:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03467","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.03467/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03467","created_at":"2026-08-05T01:35:54.693496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03467v1","created_at":"2026-08-05T01:35:54.693496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03467","created_at":"2026-08-05T01:35:54.693496+00:00"},{"alias_kind":"pith_short_12","alias_value":"656HFSJ7THBW","created_at":"2026-08-05T01:35:54.693496+00:00"},{"alias_kind":"pith_short_16","alias_value":"656HFSJ7THBWN3GH","created_at":"2026-08-05T01:35:54.693496+00:00"},{"alias_kind":"pith_short_8","alias_value":"656HFSJ7","created_at":"2026-08-05T01:35:54.693496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4","json":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4.json","graph_json":"https://pith.science/api/pith-number/656HFSJ7THBWN3GHJHQWT5MVW4/graph.json","events_json":"https://pith.science/api/pith-number/656HFSJ7THBWN3GHJHQWT5MVW4/events.json","paper":"https://pith.science/paper/656HFSJ7"},"agent_actions":{"view_html":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4","download_json":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4.json","view_paper":"https://pith.science/paper/656HFSJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03467&json=true","fetch_graph":"https://pith.science/api/pith-number/656HFSJ7THBWN3GHJHQWT5MVW4/graph.json","fetch_events":"https://pith.science/api/pith-number/656HFSJ7THBWN3GHJHQWT5MVW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4/action/storage_attestation","attest_author":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4/action/author_attestation","sign_citation":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4/action/citation_signature","submit_replication":"https://pith.science/pith/656HFSJ7THBWN3GHJHQWT5MVW4/action/replication_record"}},"created_at":"2026-08-05T01:35:54.693496+00:00","updated_at":"2026-08-05T01:35:54.693496+00:00"}