{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GEDMB5JFKJ4CLRBUANIDLYMWBP","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":"1161734287f6d3d120fec215de88fed3a674666ea2b9c929959b86e3fdfbe6b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T19:50:16Z","title_canon_sha256":"68f111c9c4e747d3f5eded399bd75c5caab4bbd0f638a570350b65801656e7cb"},"schema_version":"1.0","source":{"id":"2506.02211","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02211","created_at":"2026-07-05T11:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02211v1","created_at":"2026-07-05T11:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02211","created_at":"2026-07-05T11:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"GEDMB5JFKJ4C","created_at":"2026-07-05T11:14:34Z"},{"alias_kind":"pith_short_16","alias_value":"GEDMB5JFKJ4CLRBU","created_at":"2026-07-05T11:14:34Z"},{"alias_kind":"pith_short_8","alias_value":"GEDMB5JF","created_at":"2026-07-05T11:14:34Z"}],"graph_snapshots":[{"event_id":"sha256:6271321be48b0ccee181a9b5b7c4cf243538ecc862d85a61a5b03581457cf1d1","target":"graph","created_at":"2026-07-05T11:14:34Z","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/2506.02211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are gaining widespread use for code generation. Recent training procedures use execution feedback as a reward signal, typically focusing on the functional correctness of the code, using unit test pass rate as a reward signal. However, this reward signal fails to capture notions of maintainability, quality and safety of the code produced. We address this under-explored area and develop a comprehensive library to quantify various aspects of code quality, and use it as a reward in GRPO. We find GRPO increases code quality according to this measure, which is confirmed ","authors_text":"Laurence Aitchison, Maxime Robeyns","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T19:50:16Z","title":"Improving LLM-Generated Code Quality with GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02211","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":"sha256:0405598091cdda1dc2d86e2c670892332d433826ef08cf707456efa5846a78ee","target":"record","created_at":"2026-07-05T11:14:34Z","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":"1161734287f6d3d120fec215de88fed3a674666ea2b9c929959b86e3fdfbe6b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T19:50:16Z","title_canon_sha256":"68f111c9c4e747d3f5eded399bd75c5caab4bbd0f638a570350b65801656e7cb"},"schema_version":"1.0","source":{"id":"2506.02211","kind":"arxiv","version":1}},"canonical_sha256":"3106c0f525527825c434035035e1960be6766b4bace97b6891eb0500113d3163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3106c0f525527825c434035035e1960be6766b4bace97b6891eb0500113d3163","first_computed_at":"2026-07-05T11:14:34.457139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:34.457139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dHMAu1g1Lywip+mkdbq641iao0B6awUApZig16xV4Ld7BV58Jns71KHVtyEhjFEgjtcMXwnbe9dKyqTYolI4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:34.457613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02211","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0405598091cdda1dc2d86e2c670892332d433826ef08cf707456efa5846a78ee","sha256:6271321be48b0ccee181a9b5b7c4cf243538ecc862d85a61a5b03581457cf1d1"],"state_sha256":"7910968c0764c2dd7f2775b1afa89485d6ab3a6a821ac829b5a9143d75db4106"}