{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BYKTW2P7JN3GVP7ZP64DW7GAY7","short_pith_number":"pith:BYKTW2P7","schema_version":"1.0","canonical_sha256":"0e153b69ff4b766abff97fb83b7cc0c7d84fe2ecb85aa38ea49721b61f5c7afe","source":{"kind":"arxiv","id":"2404.08189","version":1},"attestation_state":"computed","paper":{"title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Orlando Marquez Ayala, Patrice B\\'echard","submitted_at":"2024-04-12T01:42:09Z","abstract_excerpt":"A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI systems may face challenges in user adoption. In the process of deploying an enterprise application that produces workflows based on natural language requirements, we devised a system leveraging Retrieval Augmented Generation (RAG) to greatly improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our propo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.08189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-12T01:42:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"f3e143c7aa506c0590bcd32d4ba5a2a6bc5745add4dc43228361fb4d107f82b8","abstract_canon_sha256":"87567f59f3ec2eca6d27d8e7f7a6afefbe113de15e5d8400bad64e43682bee00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:24.459081Z","signature_b64":"TTT06ys1CBoNk9/5RgVVl/qszEebPDCyEPkuVKDLtbR7jKyY0MARTnLdjBv3jcdb6cddsYaIxW1AZ4mPjBOlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e153b69ff4b766abff97fb83b7cc0c7d84fe2ecb85aa38ea49721b61f5c7afe","last_reissued_at":"2026-07-05T09:42:24.458587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:24.458587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Orlando Marquez Ayala, Patrice B\\'echard","submitted_at":"2024-04-12T01:42:09Z","abstract_excerpt":"A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI systems may face challenges in user adoption. In the process of deploying an enterprise application that produces workflows based on natural language requirements, we devised a system leveraging Retrieval Augmented Generation (RAG) to greatly improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08189","kind":"arxiv","version":1},"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/2404.08189/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.08189","created_at":"2026-07-05T09:42:24.458645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08189v1","created_at":"2026-07-05T09:42:24.458645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08189","created_at":"2026-07-05T09:42:24.458645+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYKTW2P7JN3G","created_at":"2026-07-05T09:42:24.458645+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYKTW2P7JN3GVP7Z","created_at":"2026-07-05T09:42:24.458645+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYKTW2P7","created_at":"2026-07-05T09:42:24.458645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19700","citing_title":"TerraMARS: A Domain-Adapted Small-Language-Model Pipeline for Mars Terraforming Literature","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15893","citing_title":"BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10129","citing_title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23978","citing_title":"LLM Agents Are the Antidote to Walled Gardens","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15270","citing_title":"Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7","json":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7.json","graph_json":"https://pith.science/api/pith-number/BYKTW2P7JN3GVP7ZP64DW7GAY7/graph.json","events_json":"https://pith.science/api/pith-number/BYKTW2P7JN3GVP7ZP64DW7GAY7/events.json","paper":"https://pith.science/paper/BYKTW2P7"},"agent_actions":{"view_html":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7","download_json":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7.json","view_paper":"https://pith.science/paper/BYKTW2P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08189&json=true","fetch_graph":"https://pith.science/api/pith-number/BYKTW2P7JN3GVP7ZP64DW7GAY7/graph.json","fetch_events":"https://pith.science/api/pith-number/BYKTW2P7JN3GVP7ZP64DW7GAY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7/action/storage_attestation","attest_author":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7/action/author_attestation","sign_citation":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7/action/citation_signature","submit_replication":"https://pith.science/pith/BYKTW2P7JN3GVP7ZP64DW7GAY7/action/replication_record"}},"created_at":"2026-07-05T09:42:24.458645+00:00","updated_at":"2026-07-05T09:42:24.458645+00:00"}