{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJO22QNPIQFHRKQGBVWFFLHXYV","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":"bd30b7e7770596083c577351b1b819515fca1744389c34fcdc188f56d065b9c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T17:16:03Z","title_canon_sha256":"09e0e322dbe1144fc15e8fa09eb83c61da07f15b7c54953975ece3127985ebac"},"schema_version":"1.0","source":{"id":"2406.20060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.20060","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.20060v1","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.20060","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"XJO22QNPIQFH","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"XJO22QNPIQFHRKQG","created_at":"2026-07-05T08:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"XJO22QNP","created_at":"2026-07-05T08:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:3f848c7538af1345ffc640e257d1f7199c43f3422fc22784fc2da99275089b80","target":"graph","created_at":"2026-07-05T08:37:58Z","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/2406.20060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from AI Feedback (RLAIF) has demonstrated significant potential across various domains, including mitigating harm in LLM outputs, enhancing text summarization, and mathematical reasoning. This paper introduces an RLAIF framework for improving the code generation abilities of lightweight (<1B parameters) LLMs. We specifically focus on code generation tasks that require writing appropriate API calls, which is challenging due to the well-known issue of hallucination in LLMs. Our framework extracts AI feedback from a larger LLM (e.g., GPT-3.5) through a specialized prompting","authors_text":"Bortik Bandyopadhyay, Raviteja Anantha, Sayantan Mahinder, Sujan Dutta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T17:16:03Z","title":"Applying RLAIF for Code Generation with API-usage in Lightweight LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.20060","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":"sha256:2c35fb76d177a766cb5212711f81c22562d3c2b2c4dabef17d2fcc35a8900675","target":"record","created_at":"2026-07-05T08:37:58Z","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":"bd30b7e7770596083c577351b1b819515fca1744389c34fcdc188f56d065b9c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T17:16:03Z","title_canon_sha256":"09e0e322dbe1144fc15e8fa09eb83c61da07f15b7c54953975ece3127985ebac"},"schema_version":"1.0","source":{"id":"2406.20060","kind":"arxiv","version":1}},"canonical_sha256":"ba5dad41af440a78aa060d6c52acf7c57593aca822f8388584e6a95162f2aca4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba5dad41af440a78aa060d6c52acf7c57593aca822f8388584e6a95162f2aca4","first_computed_at":"2026-07-05T08:37:58.538417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:58.538417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z7DXIKhymHGxe+Q0klAXe90IPWSvcAeCGaiirXnQ+ntDkofEtL6uvbg+JjbuyUhjiikCJX+kr+Iy6TSVwD/wCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:58.538912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.20060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c35fb76d177a766cb5212711f81c22562d3c2b2c4dabef17d2fcc35a8900675","sha256:3f848c7538af1345ffc640e257d1f7199c43f3422fc22784fc2da99275089b80"],"state_sha256":"f8a4b99b76cf4a4ca8b8669e12953293ff7efbcc13401d8f3289dbed9b9d1673"}