{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M4GPELTLRXNHZW55TYUZUFZF5A","short_pith_number":"pith:M4GPELTL","schema_version":"1.0","canonical_sha256":"670cf22e6b8dda7cdbbd9e299a1725e804a6d744e5654c45cfbd85709f706f09","source":{"kind":"arxiv","id":"2406.07070","version":1},"attestation_state":"computed","paper":{"title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyue Peng, Houfeng Wang, Richeng Xuan, Tianshu Shen, Wei Li, Wen Luo, Xi Yang","submitted_at":"2024-06-11T08:56:18Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), achieving remarkable performance across diverse tasks and enabling widespread real-world applications. However, LLMs are prone to hallucination, generating content that either conflicts with established knowledge or is unfaithful to the original sources. Existing hallucination benchmarks primarily focus on sentence- or passage-level hallucination detection, neglecting dialogue-level evaluation, hallucination localization, and rationale provision. They also predominantly target factuality ha"},"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":"2406.07070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T08:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"0aa310eebcee53fcfcba210832ff573509ab750fd3a5272b2347a69eedbb3b3d","abstract_canon_sha256":"a9b38a15a38e6dea6a1fd9299bb366669860429b218f8d308c95c5a2830f294c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:17.915379Z","signature_b64":"EgowDmvhN6a4l/cVxwQoja6rHMrTIFnm3FqhgQDJOjfN/DTiSHhSXFPGWFMvSis1fiCysn9RAJ+D3j/ZBODxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"670cf22e6b8dda7cdbbd9e299a1725e804a6d744e5654c45cfbd85709f706f09","last_reissued_at":"2026-07-05T08:30:17.914872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:17.914872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyue Peng, Houfeng Wang, Richeng Xuan, Tianshu Shen, Wei Li, Wen Luo, Xi Yang","submitted_at":"2024-06-11T08:56:18Z","abstract_excerpt":"Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), achieving remarkable performance across diverse tasks and enabling widespread real-world applications. However, LLMs are prone to hallucination, generating content that either conflicts with established knowledge or is unfaithful to the original sources. Existing hallucination benchmarks primarily focus on sentence- or passage-level hallucination detection, neglecting dialogue-level evaluation, hallucination localization, and rationale provision. They also predominantly target factuality ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07070","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/2406.07070/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":"2406.07070","created_at":"2026-07-05T08:30:17.914926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07070v1","created_at":"2026-07-05T08:30:17.914926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07070","created_at":"2026-07-05T08:30:17.914926+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4GPELTLRXNH","created_at":"2026-07-05T08:30:17.914926+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4GPELTLRXNHZW55","created_at":"2026-07-05T08:30:17.914926+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4GPELTL","created_at":"2026-07-05T08:30:17.914926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00622","citing_title":"MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06698","citing_title":"SCAN: Structured Capability Assessment and Navigation for LLMs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01749","citing_title":"Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A","json":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A.json","graph_json":"https://pith.science/api/pith-number/M4GPELTLRXNHZW55TYUZUFZF5A/graph.json","events_json":"https://pith.science/api/pith-number/M4GPELTLRXNHZW55TYUZUFZF5A/events.json","paper":"https://pith.science/paper/M4GPELTL"},"agent_actions":{"view_html":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A","download_json":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A.json","view_paper":"https://pith.science/paper/M4GPELTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07070&json=true","fetch_graph":"https://pith.science/api/pith-number/M4GPELTLRXNHZW55TYUZUFZF5A/graph.json","fetch_events":"https://pith.science/api/pith-number/M4GPELTLRXNHZW55TYUZUFZF5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A/action/storage_attestation","attest_author":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A/action/author_attestation","sign_citation":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A/action/citation_signature","submit_replication":"https://pith.science/pith/M4GPELTLRXNHZW55TYUZUFZF5A/action/replication_record"}},"created_at":"2026-07-05T08:30:17.914926+00:00","updated_at":"2026-07-05T08:30:17.914926+00:00"}