{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PWE6XCK4TB2PT3A5JLAOL3AI6Z","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":"d45f6b0a9b17020a173aef8dcf96a6cc6b17c838ecbc4790717c948cfb421410","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T04:06:41Z","title_canon_sha256":"c8788740775e2795a5524fe7b7c2dee15fe7bfcce095c376e98d3f70f9089573"},"schema_version":"1.0","source":{"id":"2607.20908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20908","created_at":"2026-07-24T01:23:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20908v1","created_at":"2026-07-24T01:23:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20908","created_at":"2026-07-24T01:23:39Z"},{"alias_kind":"pith_short_12","alias_value":"PWE6XCK4TB2P","created_at":"2026-07-24T01:23:39Z"},{"alias_kind":"pith_short_16","alias_value":"PWE6XCK4TB2PT3A5","created_at":"2026-07-24T01:23:39Z"},{"alias_kind":"pith_short_8","alias_value":"PWE6XCK4","created_at":"2026-07-24T01:23:39Z"}],"graph_snapshots":[{"event_id":"sha256:f12e00bb0b10bd98ae47ebf4a37770966fef5aa7f61c05412fa62b6cd9e4647b","target":"graph","created_at":"2026-07-24T01:23:39Z","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/2607.20908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work, we propose CudaPerf, a reflective RL framework that incorporates both verifiable execution rewards and structural code-aware rewards derived from parallelization features (e.g., memory coalescing, oc","authors_text":"Ali Jannesari, Nesreen K. Ahmed, Quazi Ishtiaque Mahmud","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T04:06:41Z","title":"Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20908","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":"sha256:03812bca47bbf1def3947932af5bb4e12504709a9bba01273cd3f4d9ac76390f","target":"record","created_at":"2026-07-24T01:23:39Z","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":"d45f6b0a9b17020a173aef8dcf96a6cc6b17c838ecbc4790717c948cfb421410","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T04:06:41Z","title_canon_sha256":"c8788740775e2795a5524fe7b7c2dee15fe7bfcce095c376e98d3f70f9089573"},"schema_version":"1.0","source":{"id":"2607.20908","kind":"arxiv","version":1}},"canonical_sha256":"7d89eb895c9874f9ec1d4ac0e5ec08f6689eed2e928de43c842292870fbe881a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d89eb895c9874f9ec1d4ac0e5ec08f6689eed2e928de43c842292870fbe881a","first_computed_at":"2026-07-24T01:23:39.930435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:39.930435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Bc55oCWHLuDEYXVMMTvLv4eEr/rapoYnFB8rMKDYXqIWV70E9kDeO6hVyzUmYKsn93FkruNM7ZE5LWqWvq6Aw==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:39.931472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03812bca47bbf1def3947932af5bb4e12504709a9bba01273cd3f4d9ac76390f","sha256:f12e00bb0b10bd98ae47ebf4a37770966fef5aa7f61c05412fa62b6cd9e4647b"],"state_sha256":"fede234ebc55c87eaf7964fbf0c3108bdbaf9c8090a6dff7b154db737ed7a3ab"}