{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4E3Y5CIOKY6J2C7KM3CF3X4ZDO","short_pith_number":"pith:4E3Y5CIO","canonical_record":{"source":{"id":"2506.11027","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:28:48Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"d9a8b6aadbe4aab7181c14fde16e7ad23ceb285bfccb1ead63e04adaefddd78d","abstract_canon_sha256":"f8a4fa354f342085db9c12e1c87a2fc3e92af8639b9b62bcafb389894c5d6d8e"},"schema_version":"1.0"},"canonical_sha256":"e1378e890e563c9d0bea66c45ddf991b91b25903f9c56d1538c2033f244e8dbb","source":{"kind":"arxiv","id":"2506.11027","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11027","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11027v3","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11027","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"4E3Y5CIOKY6J","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"4E3Y5CIOKY6J2C7K","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"4E3Y5CIO","created_at":"2026-05-26T02:03:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4E3Y5CIOKY6J2C7KM3CF3X4ZDO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11027","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:28:48Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"d9a8b6aadbe4aab7181c14fde16e7ad23ceb285bfccb1ead63e04adaefddd78d","abstract_canon_sha256":"f8a4fa354f342085db9c12e1c87a2fc3e92af8639b9b62bcafb389894c5d6d8e"},"schema_version":"1.0"},"canonical_sha256":"e1378e890e563c9d0bea66c45ddf991b91b25903f9c56d1538c2033f244e8dbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:51.792861Z","signature_b64":"iXVJnZPmaJ/P+5vuZ9wiA+TZt3KU4QYQsInxO4ogSA9ntrcXflr3ptl+eLg8otT5qFuFeGNkZH5zgMVEcPLGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1378e890e563c9d0bea66c45ddf991b91b25903f9c56d1538c2033f244e8dbb","last_reissued_at":"2026-05-26T02:03:51.791448Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:51.791448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11027","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAu2t18EIGeiOfj8tkixPlWvEQNOdQLLY0mCEIzA/ib6N785Pk5ex/DhIxUIXHRd/d2N4jL0nfa2v1/+FgV+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:26:29.211621Z"},"content_sha256":"9b200dd747a3819fdb73fc69fdec0fa1b76916f5568f2be6d779501975fb172c","schema_version":"1.0","event_id":"sha256:9b200dd747a3819fdb73fc69fdec0fa1b76916f5568f2be6d779501975fb172c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4E3Y5CIOKY6J2C7KM3CF3X4ZDO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Reasoning to Code: GRPO Optimization for Underrepresented Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Andrea Gurioli, Bianca Raimondi, Federico Pennino, Massimo Rondelli, Maurizio Gabbrielli","submitted_at":"2025-05-20T11:28:48Z","abstract_excerpt":"Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming languages, such as Prolog and Lisp, due to the scarcity of public training data compared to high-resource languages like Python. This paper introduces a generalizable Reinforcement Learning (RL) approach that combines small-scale versions of the Qwen2.5-Coder model with Group Relative Policy Optimization (GRPO) to enable effective code generation through reasoning. To address the limitations of sparse datasets, we integrate execution-driven feedback direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11027","kind":"arxiv","version":3},"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/2506.11027/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1ZQNli1JTnO15nZLk7s+wYkjtgIUK7SjX/CH5YOjwGOnf9TToGhLOgc+ewJOEQcYPM85D3Z/0hnOqatCcSGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:26:29.212009Z"},"content_sha256":"f34695d0da16f5db1e4fa0f867b19543058264575a65266504b61e51ed6de618","schema_version":"1.0","event_id":"sha256:f34695d0da16f5db1e4fa0f867b19543058264575a65266504b61e51ed6de618"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/bundle.json","state_url":"https://pith.science/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T02:26:29Z","links":{"resolver":"https://pith.science/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO","bundle":"https://pith.science/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/bundle.json","state":"https://pith.science/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4E3Y5CIOKY6J2C7KM3CF3X4ZDO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4E3Y5CIOKY6J2C7KM3CF3X4ZDO","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":"f8a4fa354f342085db9c12e1c87a2fc3e92af8639b9b62bcafb389894c5d6d8e","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:28:48Z","title_canon_sha256":"d9a8b6aadbe4aab7181c14fde16e7ad23ceb285bfccb1ead63e04adaefddd78d"},"schema_version":"1.0","source":{"id":"2506.11027","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11027","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11027v3","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11027","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"4E3Y5CIOKY6J","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"4E3Y5CIOKY6J2C7K","created_at":"2026-05-26T02:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"4E3Y5CIO","created_at":"2026-05-26T02:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:f34695d0da16f5db1e4fa0f867b19543058264575a65266504b61e51ed6de618","target":"graph","created_at":"2026-05-26T02:03:51Z","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/2506.11027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming languages, such as Prolog and Lisp, due to the scarcity of public training data compared to high-resource languages like Python. This paper introduces a generalizable Reinforcement Learning (RL) approach that combines small-scale versions of the Qwen2.5-Coder model with Group Relative Policy Optimization (GRPO) to enable effective code generation through reasoning. To address the limitations of sparse datasets, we integrate execution-driven feedback direct","authors_text":"Andrea Gurioli, Bianca Raimondi, Federico Pennino, Massimo Rondelli, Maurizio Gabbrielli","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:28:48Z","title":"From Reasoning to Code: GRPO Optimization for Underrepresented Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11027","kind":"arxiv","version":3},"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":"sha256:9b200dd747a3819fdb73fc69fdec0fa1b76916f5568f2be6d779501975fb172c","target":"record","created_at":"2026-05-26T02:03:51Z","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":"f8a4fa354f342085db9c12e1c87a2fc3e92af8639b9b62bcafb389894c5d6d8e","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:28:48Z","title_canon_sha256":"d9a8b6aadbe4aab7181c14fde16e7ad23ceb285bfccb1ead63e04adaefddd78d"},"schema_version":"1.0","source":{"id":"2506.11027","kind":"arxiv","version":3}},"canonical_sha256":"e1378e890e563c9d0bea66c45ddf991b91b25903f9c56d1538c2033f244e8dbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1378e890e563c9d0bea66c45ddf991b91b25903f9c56d1538c2033f244e8dbb","first_computed_at":"2026-05-26T02:03:51.791448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:03:51.791448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iXVJnZPmaJ/P+5vuZ9wiA+TZt3KU4QYQsInxO4ogSA9ntrcXflr3ptl+eLg8otT5qFuFeGNkZH5zgMVEcPLGDg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:03:51.792861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11027","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b200dd747a3819fdb73fc69fdec0fa1b76916f5568f2be6d779501975fb172c","sha256:f34695d0da16f5db1e4fa0f867b19543058264575a65266504b61e51ed6de618"],"state_sha256":"c0926b3afe68e3287d2670cfed1a13fd9555d4a02b751daf90c685c45df87aa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J1juMxEfT6QzxZ5yvpoXj2v1ddvR0UmaXbdkEyVgJxsapKWdRIbeJ8RAgHczB7qFPDn8FnjqF348qxc0yRxqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:26:29.214149Z","bundle_sha256":"f742ca6cb47c45a7edd4ccdf942ff98f289d40d14cddf48fc32f32f7c5540a0d"}}