{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:75B2TBSRUCGPVGRCB3MWLPFD7L","short_pith_number":"pith:75B2TBSR","schema_version":"1.0","canonical_sha256":"ff43a98651a08cfa9a220ed965bca3facc276048ca43289dc51126f713c0b36b","source":{"kind":"arxiv","id":"2412.05223","version":2},"attestation_state":"computed","paper":{"title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam A. Forbes, Michael C. Wood","submitted_at":"2024-12-06T17:54:54Z","abstract_excerpt":"The issue of hallucinations in large language models (LLMs) remains a critical barrier to the adoption of AI in enterprise and other high-stakes applications. Despite advancements in retrieval-augmented generation (RAG) systems, current state-of-the-art methods fail to achieve more than 80% accuracy in generating faithful and factually correct outputs, even when provided with relevant and accurate context. In this work, we introduce Acurai, a novel systematic approach that achieves 100% hallucination-free responses in LLMs by reformatting queries and context data prior to input. Leveraging a d"},"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":"2412.05223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T17:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"65b8e0bce626f9256e13fd81827c69a31690239cb29502ec8d2d1769ce81dff5","abstract_canon_sha256":"afcefb1a78f5fa8c6e3a9f4f05b66142262b6e44f8e7a857da8a6a85aad8ac61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:24.091141Z","signature_b64":"RD0KTiIglcuG4Rk9J71PL9KQPMX3qgGJe21I/9pN6EofcQrWL0Nf/O1WblkPELddpPvS/g6uNf5NpKYDNfVkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff43a98651a08cfa9a220ed965bca3facc276048ca43289dc51126f713c0b36b","last_reissued_at":"2026-07-05T10:39:24.090649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:24.090649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam A. Forbes, Michael C. Wood","submitted_at":"2024-12-06T17:54:54Z","abstract_excerpt":"The issue of hallucinations in large language models (LLMs) remains a critical barrier to the adoption of AI in enterprise and other high-stakes applications. Despite advancements in retrieval-augmented generation (RAG) systems, current state-of-the-art methods fail to achieve more than 80% accuracy in generating faithful and factually correct outputs, even when provided with relevant and accurate context. In this work, we introduce Acurai, a novel systematic approach that achieves 100% hallucination-free responses in LLMs by reformatting queries and context data prior to input. Leveraging a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05223","kind":"arxiv","version":2},"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/2412.05223/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":"2412.05223","created_at":"2026-07-05T10:39:24.090708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05223v2","created_at":"2026-07-05T10:39:24.090708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05223","created_at":"2026-07-05T10:39:24.090708+00:00"},{"alias_kind":"pith_short_12","alias_value":"75B2TBSRUCGP","created_at":"2026-07-05T10:39:24.090708+00:00"},{"alias_kind":"pith_short_16","alias_value":"75B2TBSRUCGPVGRC","created_at":"2026-07-05T10:39:24.090708+00:00"},{"alias_kind":"pith_short_8","alias_value":"75B2TBSR","created_at":"2026-07-05T10:39:24.090708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09073","citing_title":"Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L","json":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L.json","graph_json":"https://pith.science/api/pith-number/75B2TBSRUCGPVGRCB3MWLPFD7L/graph.json","events_json":"https://pith.science/api/pith-number/75B2TBSRUCGPVGRCB3MWLPFD7L/events.json","paper":"https://pith.science/paper/75B2TBSR"},"agent_actions":{"view_html":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L","download_json":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L.json","view_paper":"https://pith.science/paper/75B2TBSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05223&json=true","fetch_graph":"https://pith.science/api/pith-number/75B2TBSRUCGPVGRCB3MWLPFD7L/graph.json","fetch_events":"https://pith.science/api/pith-number/75B2TBSRUCGPVGRCB3MWLPFD7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L/action/storage_attestation","attest_author":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L/action/author_attestation","sign_citation":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L/action/citation_signature","submit_replication":"https://pith.science/pith/75B2TBSRUCGPVGRCB3MWLPFD7L/action/replication_record"}},"created_at":"2026-07-05T10:39:24.090708+00:00","updated_at":"2026-07-05T10:39:24.090708+00:00"}