{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YVFSOUNMIXAAQ5ARO4DNGUVMX5","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":"838d2109150f60fdb640b456794af01a62fd86a774125e416c47d1298206e20e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2023-05-25T22:09:08Z","title_canon_sha256":"d600772fdbe43fa439e7e5aac6ff5055640fe2f1c75758395e0fda24ff90b439"},"schema_version":"1.0","source":{"id":"2305.18341","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18341","created_at":"2026-07-05T07:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18341v2","created_at":"2026-07-05T07:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18341","created_at":"2026-07-05T07:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"YVFSOUNMIXAA","created_at":"2026-07-05T07:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"YVFSOUNMIXAAQ5AR","created_at":"2026-07-05T07:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"YVFSOUNM","created_at":"2026-07-05T07:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:c2e994636b59056f338a3d39c7a8d507186bccf3f11286d0a02bea0822738b67","target":"graph","created_at":"2026-07-05T07:27:25Z","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/2305.18341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose RLCF, that further trains a pre-trained LLM via reinforcement learning, using feedback from a grounding function that scores the quality of the code. The grounding function uses (i) compiler-derived feedback on whether the code it generates passes a set of correctness checks; and (ii) feedback from a different LLM that compares the generated code to a refere","authors_text":"(2) UT Austin, (3) University of Wisconsin), Abhinav Jain (1), Chima Adiole (1), Chris Jermaine (1) ((1) Rice University, Swarat Chaudhuri (2), Thomas Reps (3)","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2023-05-25T22:09:08Z","title":"Coarse-Tuning Models of Code with Reinforcement Learning Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18341","kind":"arxiv","version":2},"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":"sha256:6f6d0733824f27dda1c635031b43402994553d356797e4ac3b1d8759911095eb","target":"record","created_at":"2026-07-05T07:27:25Z","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":"838d2109150f60fdb640b456794af01a62fd86a774125e416c47d1298206e20e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2023-05-25T22:09:08Z","title_canon_sha256":"d600772fdbe43fa439e7e5aac6ff5055640fe2f1c75758395e0fda24ff90b439"},"schema_version":"1.0","source":{"id":"2305.18341","kind":"arxiv","version":2}},"canonical_sha256":"c54b2751ac45c00874117706d352acbf5e210e8f59e1647727777dc6bae5cc0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c54b2751ac45c00874117706d352acbf5e210e8f59e1647727777dc6bae5cc0c","first_computed_at":"2026-07-05T07:27:25.314109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:25.314109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bp8T4kIv20QXFfI0qYiSMxQQo7RLHliJuGDeXErsnn3G9u84AL+E5Vb2rLls3TI4NnEc3SB7HDycpt0p136vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:25.314749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18341","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f6d0733824f27dda1c635031b43402994553d356797e4ac3b1d8759911095eb","sha256:c2e994636b59056f338a3d39c7a8d507186bccf3f11286d0a02bea0822738b67"],"state_sha256":"291abe60b6eef7c156488eb14f8575402ca5d4f276eda4a2f9822ced9fe007f7"}