{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XNMC3MFNCBNGK5D7MPR3IMBIU7","short_pith_number":"pith:XNMC3MFN","schema_version":"1.0","canonical_sha256":"bb582db0ad105a65747f63e3b43028a7f5a15386f5a033b0b3a0e284e455003f","source":{"kind":"arxiv","id":"2310.06498","version":2},"attestation_state":"computed","paper":{"title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Renliang Sun, Shiping Yang, Xiaojun Wan","submitted_at":"2023-10-10T10:14:59Z","abstract_excerpt":"Large Language Models (LLMs) have shown their ability to collaborate effectively with humans in real-world scenarios. However, LLMs are apt to generate hallucinations, i.e., makeup incorrect text and unverified information, which can cause significant damage when deployed for mission-critical tasks. In this paper, we propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. To facilitate future studies and assess different methods, we construct a hallucination detection benchmark named PHD, which is generated by ChatGPT and ann"},"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":"2310.06498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T10:14:59Z","cross_cats_sorted":[],"title_canon_sha256":"8a56cfd93c5f9a25ddb1a840eb5f498e477d683cb66cac04bea5ae8162113638","abstract_canon_sha256":"d187c726910cee9059779932308e320c9bd904a5551a614bb7bc3c9ee00bdb77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:21.295171Z","signature_b64":"tcO8AwnfTkP0/GvcsBKU2E/Px2AA+7PxinNzs0DgVf1D8k2a0r4CN8y1vslA0UQPv5k5+Z6xuYqyJ/xmlHfEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb582db0ad105a65747f63e3b43028a7f5a15386f5a033b0b3a0e284e455003f","last_reissued_at":"2026-07-05T07:04:21.294708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:21.294708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Renliang Sun, Shiping Yang, Xiaojun Wan","submitted_at":"2023-10-10T10:14:59Z","abstract_excerpt":"Large Language Models (LLMs) have shown their ability to collaborate effectively with humans in real-world scenarios. However, LLMs are apt to generate hallucinations, i.e., makeup incorrect text and unverified information, which can cause significant damage when deployed for mission-critical tasks. In this paper, we propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. To facilitate future studies and assess different methods, we construct a hallucination detection benchmark named PHD, which is generated by ChatGPT and ann"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06498","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/2310.06498/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":"2310.06498","created_at":"2026-07-05T07:04:21.294764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06498v2","created_at":"2026-07-05T07:04:21.294764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06498","created_at":"2026-07-05T07:04:21.294764+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNMC3MFNCBNG","created_at":"2026-07-05T07:04:21.294764+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNMC3MFNCBNGK5D7","created_at":"2026-07-05T07:04:21.294764+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNMC3MFN","created_at":"2026-07-05T07:04:21.294764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06539","citing_title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7","json":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7.json","graph_json":"https://pith.science/api/pith-number/XNMC3MFNCBNGK5D7MPR3IMBIU7/graph.json","events_json":"https://pith.science/api/pith-number/XNMC3MFNCBNGK5D7MPR3IMBIU7/events.json","paper":"https://pith.science/paper/XNMC3MFN"},"agent_actions":{"view_html":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7","download_json":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7.json","view_paper":"https://pith.science/paper/XNMC3MFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06498&json=true","fetch_graph":"https://pith.science/api/pith-number/XNMC3MFNCBNGK5D7MPR3IMBIU7/graph.json","fetch_events":"https://pith.science/api/pith-number/XNMC3MFNCBNGK5D7MPR3IMBIU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7/action/storage_attestation","attest_author":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7/action/author_attestation","sign_citation":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7/action/citation_signature","submit_replication":"https://pith.science/pith/XNMC3MFNCBNGK5D7MPR3IMBIU7/action/replication_record"}},"created_at":"2026-07-05T07:04:21.294764+00:00","updated_at":"2026-07-05T07:04:21.294764+00:00"}