{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GZOK2CQW3P3XTJQSHA4W2YRGIJ","short_pith_number":"pith:GZOK2CQW","schema_version":"1.0","canonical_sha256":"365cad0a16dbf779a61238396d62264245daab893aca063832b82c69253bfbd6","source":{"kind":"arxiv","id":"2605.24331","version":1},"attestation_state":"computed","paper":{"title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayi Xin, Ke Sun, Qi Long, Weijie Su, Yizhou Zhao","submitted_at":"2026-05-23T01:18:55Z","abstract_excerpt":"Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the reasoning capability of large language models, yet the principle determining what constitutes an optimal weighting remains poorly understood. We address this gap by formulating prompt reweighting as a functional derivative of a utility functional defined in the pass-rate function space, yielding a unified optimality framework that accommodates existing schemes, including REINFORCE and GRPO. Building on this optimality framework, we propose a di"},"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":"2605.24331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T01:18:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"051df171152a972a337de7957e7568e6dfd4abdd6d0a05d8a286fb1d50164f2c","abstract_canon_sha256":"be9aee2f416b40b92f2638ac5185b54c73d07c3bfd56ef9d8f1e170bef12f465"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:00.386001Z","signature_b64":"j8hnsYR7EskZCNZBS4/OQbveqHIT6TiEJz2zydkTHkxWtBvA4lPgUh9X6m8w/XRByiSIje6YKB+Hvj2XdW+NBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"365cad0a16dbf779a61238396d62264245daab893aca063832b82c69253bfbd6","last_reissued_at":"2026-05-26T01:03:00.385144Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:00.385144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayi Xin, Ke Sun, Qi Long, Weijie Su, Yizhou Zhao","submitted_at":"2026-05-23T01:18:55Z","abstract_excerpt":"Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the reasoning capability of large language models, yet the principle determining what constitutes an optimal weighting remains poorly understood. We address this gap by formulating prompt reweighting as a functional derivative of a utility functional defined in the pass-rate function space, yielding a unified optimality framework that accommodates existing schemes, including REINFORCE and GRPO. Building on this optimality framework, we propose a di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24331","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/2605.24331/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":"2605.24331","created_at":"2026-05-26T01:03:00.385293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24331v1","created_at":"2026-05-26T01:03:00.385293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24331","created_at":"2026-05-26T01:03:00.385293+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZOK2CQW3P3X","created_at":"2026-05-26T01:03:00.385293+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZOK2CQW3P3XTJQS","created_at":"2026-05-26T01:03:00.385293+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZOK2CQW","created_at":"2026-05-26T01:03:00.385293+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/GZOK2CQW3P3XTJQSHA4W2YRGIJ","json":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ.json","graph_json":"https://pith.science/api/pith-number/GZOK2CQW3P3XTJQSHA4W2YRGIJ/graph.json","events_json":"https://pith.science/api/pith-number/GZOK2CQW3P3XTJQSHA4W2YRGIJ/events.json","paper":"https://pith.science/paper/GZOK2CQW"},"agent_actions":{"view_html":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ","download_json":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ.json","view_paper":"https://pith.science/paper/GZOK2CQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24331&json=true","fetch_graph":"https://pith.science/api/pith-number/GZOK2CQW3P3XTJQSHA4W2YRGIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GZOK2CQW3P3XTJQSHA4W2YRGIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ/action/storage_attestation","attest_author":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ/action/author_attestation","sign_citation":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ/action/citation_signature","submit_replication":"https://pith.science/pith/GZOK2CQW3P3XTJQSHA4W2YRGIJ/action/replication_record"}},"created_at":"2026-05-26T01:03:00.385293+00:00","updated_at":"2026-05-26T01:03:00.385293+00:00"}