{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YRNXSMMVNLALORYECFTIKNYEE","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":"870a2a9629be125dc01eff905183d79433a5ca41af00f19cd6aeb7965dee50b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T15:38:55Z","title_canon_sha256":"ddb39efa62de13ceb0e1492ed7e055fe103c98b9b71be9f6fec1f7be349cf0f4"},"schema_version":"1.0","source":{"id":"2403.00896","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00896","created_at":"2026-07-05T09:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00896v3","created_at":"2026-07-05T09:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00896","created_at":"2026-07-05T09:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"3YRNXSMMVNLA","created_at":"2026-07-05T09:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"3YRNXSMMVNLALORY","created_at":"2026-07-05T09:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"3YRNXSMM","created_at":"2026-07-05T09:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:ca1a97bdd84119ba2d075896d6ed0fa1c9bbdb8ee29d4620c4dc2a2947015f59","target":"graph","created_at":"2026-07-05T09:18:23Z","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/2403.00896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since large language models (LLMs) achieve significant success in recent years, the hallucination issue remains a challenge, numerous benchmarks are proposed to detect the hallucination. Nevertheless, some of these benchmarks are not naturally generated by LLMs but are intentionally induced. Also, many merely focus on the factuality hallucination while ignoring the faithfulness hallucination. Additionally, although dialogue pattern is more widely utilized in the era of LLMs, current benchmarks only concentrate on sentence-level and passage-level hallucination. In this study, we propose DiaHalu","authors_text":"Jie Zhou, Kedi Chen, Liang He, Qin Chen, Yishen He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T15:38:55Z","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00896","kind":"arxiv","version":3},"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:adf06a42413ca32d49e8b442e557852241d5d9272c459579c05ea420b1d39fb4","target":"record","created_at":"2026-07-05T09:18:23Z","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":"870a2a9629be125dc01eff905183d79433a5ca41af00f19cd6aeb7965dee50b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T15:38:55Z","title_canon_sha256":"ddb39efa62de13ceb0e1492ed7e055fe103c98b9b71be9f6fec1f7be349cf0f4"},"schema_version":"1.0","source":{"id":"2403.00896","kind":"arxiv","version":3}},"canonical_sha256":"de22dbc98cab5605ba38208b3429b821033725e7bcfed273cd82d317d4622ce6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de22dbc98cab5605ba38208b3429b821033725e7bcfed273cd82d317d4622ce6","first_computed_at":"2026-07-05T09:18:23.619921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:23.619921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hr1FwC3FyBkSulpT490IlSVFwe0hT9FbzfknwgiX5CKqdWasWq+5oO/2CFt7uGA3lI7Tavl7bNRnDJh6QwhjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:23.620521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00896","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adf06a42413ca32d49e8b442e557852241d5d9272c459579c05ea420b1d39fb4","sha256:ca1a97bdd84119ba2d075896d6ed0fa1c9bbdb8ee29d4620c4dc2a2947015f59"],"state_sha256":"05a5e5fef587478fc0d8df623bcac47229a9c672adf2a89d03ef5864215a9946"}