{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZMMNP36SSQ4XYFGSYXLHFYE2LG","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":"4c76b6a694bcc41a13d04ccf82a78ba89c5b17dc4edfa01ef9414304e1effa2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T23:25:17Z","title_canon_sha256":"c50d4ca167ea926f2ce1754c14aa653203c62ca9daccd440508ac00dff7e6d4b"},"schema_version":"1.0","source":{"id":"2410.02089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02089","created_at":"2026-07-05T10:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02089v2","created_at":"2026-07-05T10:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02089","created_at":"2026-07-05T10:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZMMNP36SSQ4X","created_at":"2026-07-05T10:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZMMNP36SSQ4XYFGS","created_at":"2026-07-05T10:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZMMNP36S","created_at":"2026-07-05T10:16:13Z"}],"graph_snapshots":[{"event_id":"sha256:04e63d17828a12652fd30f1a380c5e5794258034acdde01865f571cd69f8a540","target":"graph","created_at":"2026-07-05T10:16:13Z","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/2410.02089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need to ground their generations in any feedback obtained to reliably achieve the desired outcomes. We propose an end-to-end reinforcement learning method for teaching models to leverage execution feedback in the realm of code synthesis, where state-of-the-art LLMs struggle to improve code iteratively compared to independent sampling. We benchmark on competitive programming tasks, where we achieve new state-of-the art res","authors_text":"Gabriel Synnaeve, Jade Copet, Jonas Gehring, Kunhao Zheng, Quentin Carbonneaux, Taco Cohen, Vegard Mella","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T23:25:17Z","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02089","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:ef1cb2157bcd5599d7f9f5470844fe88beb2b045a52c5a151d3a4c57f32ee920","target":"record","created_at":"2026-07-05T10:16:13Z","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":"4c76b6a694bcc41a13d04ccf82a78ba89c5b17dc4edfa01ef9414304e1effa2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T23:25:17Z","title_canon_sha256":"c50d4ca167ea926f2ce1754c14aa653203c62ca9daccd440508ac00dff7e6d4b"},"schema_version":"1.0","source":{"id":"2410.02089","kind":"arxiv","version":2}},"canonical_sha256":"cb18d7efd294397c14d2c5d672e09a59a5cea078a2802c450e4074ee254c93cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb18d7efd294397c14d2c5d672e09a59a5cea078a2802c450e4074ee254c93cf","first_computed_at":"2026-07-05T10:16:13.316085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:13.316085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DA/OR+GD52Vm89An/64OaiRYuSz2GYG9lbfvB6R8OQ4QIJTAY6ZJYuta/cVaw1I2b0luySMkpus7lB5JOR7VDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:13.316625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef1cb2157bcd5599d7f9f5470844fe88beb2b045a52c5a151d3a4c57f32ee920","sha256:04e63d17828a12652fd30f1a380c5e5794258034acdde01865f571cd69f8a540"],"state_sha256":"73dac217a516dd1176e537643283ec63c0771c8988cfd98d78faa055c3bfe7c2"}