{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XNMC3MFNCBNGK5D7MPR3IMBIU7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d187c726910cee9059779932308e320c9bd904a5551a614bb7bc3c9ee00bdb77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T10:14:59Z","title_canon_sha256":"8a56cfd93c5f9a25ddb1a840eb5f498e477d683cb66cac04bea5ae8162113638"},"schema_version":"1.0","source":{"id":"2310.06498","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06498","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06498v2","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06498","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"XNMC3MFNCBNG","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"XNMC3MFNCBNGK5D7","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"XNMC3MFN","created_at":"2026-07-05T07:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:0f128d02d3a4d04674b2f0c0a98cf08bf5d3ec077eb0f6b2cf7e31bf5d443a80","target":"graph","created_at":"2026-07-05T07:04:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.06498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Renliang Sun, Shiping Yang, Xiaojun Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T10:14:59Z","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06498","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95f0339b682feca02eea1d6ba2065ac60ffa3bdb9b773f05512134e71ae9ba2b","target":"record","created_at":"2026-07-05T07:04:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d187c726910cee9059779932308e320c9bd904a5551a614bb7bc3c9ee00bdb77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T10:14:59Z","title_canon_sha256":"8a56cfd93c5f9a25ddb1a840eb5f498e477d683cb66cac04bea5ae8162113638"},"schema_version":"1.0","source":{"id":"2310.06498","kind":"arxiv","version":2}},"canonical_sha256":"bb582db0ad105a65747f63e3b43028a7f5a15386f5a033b0b3a0e284e455003f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb582db0ad105a65747f63e3b43028a7f5a15386f5a033b0b3a0e284e455003f","first_computed_at":"2026-07-05T07:04:21.294708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:21.294708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcO8AwnfTkP0/GvcsBKU2E/Px2AA+7PxinNzs0DgVf1D8k2a0r4CN8y1vslA0UQPv5k5+Z6xuYqyJ/xmlHfEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:21.295171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06498","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95f0339b682feca02eea1d6ba2065ac60ffa3bdb9b773f05512134e71ae9ba2b","sha256:0f128d02d3a4d04674b2f0c0a98cf08bf5d3ec077eb0f6b2cf7e31bf5d443a80"],"state_sha256":"4f0c489563fca333879fc7391486541f2edd80b19cb4597651c1cfcf0b99b559"}