{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7W5N6FZWA76DPAORYCXT6TZLH7","short_pith_number":"pith:7W5N6FZW","schema_version":"1.0","canonical_sha256":"fdbadf173607fc3781d1c0af3f4f2b3ff9817d3921d4976ce2c53035c3992b8b","source":{"kind":"arxiv","id":"2310.12086","version":3},"attestation_state":"computed","paper":{"title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengfei Lv, Chenxi Wang, Dan Zhang, Duanzheng Song, Fei Huang, Honghao Gui, Huajun Chen, Ningyu Zhang, Xiang Chen, Yong Jiang","submitted_at":"2023-10-18T16:27:49Z","abstract_excerpt":"Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications. The accurate identification of hallucinations in texts generated by LLMs, especially in complex inferential scenarios, is a relatively unexplored area. To address this gap, we present FactCHD, a dedicated benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. A distinctive element of FactCHD is its integ"},"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":"2310.12086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T16:27:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"53369d1df7cac9ac1c1f3968895717d2e605ca8c4c0e4cc2930d111360ecca3a","abstract_canon_sha256":"9e3a0fe544ecf93e812eacb5478f5f368e2c9359e1d681262c71b1be91dbe9a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:12.996280Z","signature_b64":"xbnHkhaYi5vXU7GvlFikF57CDWQxL2ouH/X/8RweRG5HZ/U9GGsTtlyyoAgZ4QjFeBkkieUU6KnCNzb8d3B0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdbadf173607fc3781d1c0af3f4f2b3ff9817d3921d4976ce2c53035c3992b8b","last_reissued_at":"2026-07-05T08:23:12.995838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:12.995838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengfei Lv, Chenxi Wang, Dan Zhang, Duanzheng Song, Fei Huang, Honghao Gui, Huajun Chen, Ningyu Zhang, Xiang Chen, Yong Jiang","submitted_at":"2023-10-18T16:27:49Z","abstract_excerpt":"Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications. The accurate identification of hallucinations in texts generated by LLMs, especially in complex inferential scenarios, is a relatively unexplored area. To address this gap, we present FactCHD, a dedicated benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. A distinctive element of FactCHD is its integ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12086","kind":"arxiv","version":3},"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/2310.12086/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":"2310.12086","created_at":"2026-07-05T08:23:12.995895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12086v3","created_at":"2026-07-05T08:23:12.995895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12086","created_at":"2026-07-05T08:23:12.995895+00:00"},{"alias_kind":"pith_short_12","alias_value":"7W5N6FZWA76D","created_at":"2026-07-05T08:23:12.995895+00:00"},{"alias_kind":"pith_short_16","alias_value":"7W5N6FZWA76DPAOR","created_at":"2026-07-05T08:23:12.995895+00:00"},{"alias_kind":"pith_short_8","alias_value":"7W5N6FZW","created_at":"2026-07-05T08:23:12.995895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":156,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7","json":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7.json","graph_json":"https://pith.science/api/pith-number/7W5N6FZWA76DPAORYCXT6TZLH7/graph.json","events_json":"https://pith.science/api/pith-number/7W5N6FZWA76DPAORYCXT6TZLH7/events.json","paper":"https://pith.science/paper/7W5N6FZW"},"agent_actions":{"view_html":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7","download_json":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7.json","view_paper":"https://pith.science/paper/7W5N6FZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12086&json=true","fetch_graph":"https://pith.science/api/pith-number/7W5N6FZWA76DPAORYCXT6TZLH7/graph.json","fetch_events":"https://pith.science/api/pith-number/7W5N6FZWA76DPAORYCXT6TZLH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7/action/storage_attestation","attest_author":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7/action/author_attestation","sign_citation":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7/action/citation_signature","submit_replication":"https://pith.science/pith/7W5N6FZWA76DPAORYCXT6TZLH7/action/replication_record"}},"created_at":"2026-07-05T08:23:12.995895+00:00","updated_at":"2026-07-05T08:23:12.995895+00:00"}