{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2GYZSUCLI4UHRXGPAGOZ3LCXRH","short_pith_number":"pith:2GYZSUCL","schema_version":"1.0","canonical_sha256":"d1b199504b472878dccf019d9dac5789ded5d9db94cb0edf8b8bd268d1afc0e9","source":{"kind":"arxiv","id":"2311.09114","version":2},"attestation_state":"computed","paper":{"title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoqiang Kang, Huaxiu Yao, Juntong Ni","submitted_at":"2023-11-15T17:04:56Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text. However, they often encounter the challenge of generating inaccurate or hallucinated content. This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the \"snowballing\" issue, especially in reasoning tasks. To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever). Instead of wa"},"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":"2311.09114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T17:04:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"caa8af972ed6c35b3d27a464e3eace15ff6a0db0cd8f399f68906cfa79459300","abstract_canon_sha256":"c77d0d10e467fc42a20b58de1e156e68b28681395b84a11a2062b1bb9dad4bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:50.270257Z","signature_b64":"jdY7CRNxcaVBovkCB2bjB+zQpM6DIo8yGhZwn0zCwXTR7e8QDWw9nZuJVfOKn/r96F4JwgICdim8cKNbaSUIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1b199504b472878dccf019d9dac5789ded5d9db94cb0edf8b8bd268d1afc0e9","last_reissued_at":"2026-07-05T07:48:50.269823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:50.269823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoqiang Kang, Huaxiu Yao, Juntong Ni","submitted_at":"2023-11-15T17:04:56Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text. However, they often encounter the challenge of generating inaccurate or hallucinated content. This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the \"snowballing\" issue, especially in reasoning tasks. To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever). Instead of wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09114","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/2311.09114/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":"2311.09114","created_at":"2026-07-05T07:48:50.269880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09114v2","created_at":"2026-07-05T07:48:50.269880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09114","created_at":"2026-07-05T07:48:50.269880+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GYZSUCLI4UH","created_at":"2026-07-05T07:48:50.269880+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GYZSUCLI4UHRXGP","created_at":"2026-07-05T07:48:50.269880+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GYZSUCL","created_at":"2026-07-05T07:48:50.269880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04435","citing_title":"Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH","json":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH.json","graph_json":"https://pith.science/api/pith-number/2GYZSUCLI4UHRXGPAGOZ3LCXRH/graph.json","events_json":"https://pith.science/api/pith-number/2GYZSUCLI4UHRXGPAGOZ3LCXRH/events.json","paper":"https://pith.science/paper/2GYZSUCL"},"agent_actions":{"view_html":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH","download_json":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH.json","view_paper":"https://pith.science/paper/2GYZSUCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09114&json=true","fetch_graph":"https://pith.science/api/pith-number/2GYZSUCLI4UHRXGPAGOZ3LCXRH/graph.json","fetch_events":"https://pith.science/api/pith-number/2GYZSUCLI4UHRXGPAGOZ3LCXRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH/action/storage_attestation","attest_author":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH/action/author_attestation","sign_citation":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH/action/citation_signature","submit_replication":"https://pith.science/pith/2GYZSUCLI4UHRXGPAGOZ3LCXRH/action/replication_record"}},"created_at":"2026-07-05T07:48:50.269880+00:00","updated_at":"2026-07-05T07:48:50.269880+00:00"}