{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYRPRPPRINO4OZMPSIGNP3N5SV","short_pith_number":"pith:GYRPRPPR","schema_version":"1.0","canonical_sha256":"3622f8bdf1435dc7658f920cd7edbd95446c9316fa8a13d754c0df3ea4d1d9a1","source":{"kind":"arxiv","id":"2311.13878","version":1},"attestation_state":"computed","paper":{"title":"Minimizing Factual Inconsistency and Hallucination in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Advaith Shankar, Muneeswaran I, M V Sai Prakash, Saisubramaniam Gopalakrishnan, Shreya Saxena, Siva Prasad, Varun V, Vishal Vaddina","submitted_at":"2023-11-23T09:58:39Z","abstract_excerpt":"Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance due to their remarkable proficiency in various language-related tasks. However, LLMs are prone to generating factually incorrect responses or \"hallucinations,\" which can lead to a loss of credibility and trust among users. To address this issue, we propose a multi-stage framework that generates the rationale first, verifies and refines incorrect ones, and uses them as supporting references to generate the answer. The generated rationale enhances the transparency of the answer and our fram"},"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":"2311.13878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-23T09:58:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a549ef1eb7c4c19d72ea7a8366835ae31cb2a09405c5f723cc3c53fea469fc21","abstract_canon_sha256":"e3a026631eeadf8e3f2743f6977105638e857d40e2b4010198e3d2bf27fc0455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:09.552807Z","signature_b64":"dklre0FvTNoBM44oNBw36WYr/xKy1f4pySFB51vETwKg3C2iJ807VYQL4dJLlTnJ2pwn7SVNO6VhORi/fTjmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3622f8bdf1435dc7658f920cd7edbd95446c9316fa8a13d754c0df3ea4d1d9a1","last_reissued_at":"2026-07-05T07:16:09.552320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:09.552320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimizing Factual Inconsistency and Hallucination in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Advaith Shankar, Muneeswaran I, M V Sai Prakash, Saisubramaniam Gopalakrishnan, Shreya Saxena, Siva Prasad, Varun V, Vishal Vaddina","submitted_at":"2023-11-23T09:58:39Z","abstract_excerpt":"Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance due to their remarkable proficiency in various language-related tasks. However, LLMs are prone to generating factually incorrect responses or \"hallucinations,\" which can lead to a loss of credibility and trust among users. To address this issue, we propose a multi-stage framework that generates the rationale first, verifies and refines incorrect ones, and uses them as supporting references to generate the answer. The generated rationale enhances the transparency of the answer and our fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13878","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/2311.13878/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":"2311.13878","created_at":"2026-07-05T07:16:09.552380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13878v1","created_at":"2026-07-05T07:16:09.552380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13878","created_at":"2026-07-05T07:16:09.552380+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYRPRPPRINO4","created_at":"2026-07-05T07:16:09.552380+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYRPRPPRINO4OZMP","created_at":"2026-07-05T07:16:09.552380+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYRPRPPR","created_at":"2026-07-05T07:16:09.552380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04666","citing_title":"Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV","json":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV.json","graph_json":"https://pith.science/api/pith-number/GYRPRPPRINO4OZMPSIGNP3N5SV/graph.json","events_json":"https://pith.science/api/pith-number/GYRPRPPRINO4OZMPSIGNP3N5SV/events.json","paper":"https://pith.science/paper/GYRPRPPR"},"agent_actions":{"view_html":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV","download_json":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV.json","view_paper":"https://pith.science/paper/GYRPRPPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13878&json=true","fetch_graph":"https://pith.science/api/pith-number/GYRPRPPRINO4OZMPSIGNP3N5SV/graph.json","fetch_events":"https://pith.science/api/pith-number/GYRPRPPRINO4OZMPSIGNP3N5SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV/action/storage_attestation","attest_author":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV/action/author_attestation","sign_citation":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV/action/citation_signature","submit_replication":"https://pith.science/pith/GYRPRPPRINO4OZMPSIGNP3N5SV/action/replication_record"}},"created_at":"2026-07-05T07:16:09.552380+00:00","updated_at":"2026-07-05T07:16:09.552380+00:00"}