{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WYQRPHGDM2KWPEVGBRSXRIIHBW","short_pith_number":"pith:WYQRPHGD","schema_version":"1.0","canonical_sha256":"b621179cc366956792a60c6578a1070d84eaedceeaa245b09f53320e0543b6fd","source":{"kind":"arxiv","id":"2310.07289","version":1},"attestation_state":"computed","paper":{"title":"Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingzhe Wu, Kam-Fai Wong, Liang Chen, Tat-Seng Chua, Yang Deng, Yatao Bian, Zeyu Qin","submitted_at":"2023-10-11T08:22:37Z","abstract_excerpt":"Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. In light of this, we introduce CONNER, a COmpreheNsive kNowledge Evaluation fRamework, designed to systematically and automatically evaluate generated knowledge from six important perspectives -- Factuality, Relevance, Coherence, Informativeness, Helpfulness and Validity. We conduct an extensive empirical analysi"},"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":"2310.07289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T08:22:37Z","cross_cats_sorted":[],"title_canon_sha256":"10a79404690a83fd5dcb8e8b5bd4f08f35299b4d0bdcf3617981a34da585fe1a","abstract_canon_sha256":"73e5dbe6dd6f3b98c7f4bca7571c8f0ba731e131b6d384bda3a3edcec8c9649d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:43.398378Z","signature_b64":"0HutHiGPaZ0PLBRakbH7yJ0fVhus00WwOJZKQWf/FwrLp/6MDc7GcaDUS0sVf2+tGzc4NqrDInGSk595mhm/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b621179cc366956792a60c6578a1070d84eaedceeaa245b09f53320e0543b6fd","last_reissued_at":"2026-07-05T06:59:43.397862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:43.397862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingzhe Wu, Kam-Fai Wong, Liang Chen, Tat-Seng Chua, Yang Deng, Yatao Bian, Zeyu Qin","submitted_at":"2023-10-11T08:22:37Z","abstract_excerpt":"Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. In light of this, we introduce CONNER, a COmpreheNsive kNowledge Evaluation fRamework, designed to systematically and automatically evaluate generated knowledge from six important perspectives -- Factuality, Relevance, Coherence, Informativeness, Helpfulness and Validity. We conduct an extensive empirical analysi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07289","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/2310.07289/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":"2310.07289","created_at":"2026-07-05T06:59:43.397921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07289v1","created_at":"2026-07-05T06:59:43.397921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07289","created_at":"2026-07-05T06:59:43.397921+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYQRPHGDM2KW","created_at":"2026-07-05T06:59:43.397921+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYQRPHGDM2KWPEVG","created_at":"2026-07-05T06:59:43.397921+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYQRPHGD","created_at":"2026-07-05T06:59:43.397921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22865","citing_title":"ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW","json":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW.json","graph_json":"https://pith.science/api/pith-number/WYQRPHGDM2KWPEVGBRSXRIIHBW/graph.json","events_json":"https://pith.science/api/pith-number/WYQRPHGDM2KWPEVGBRSXRIIHBW/events.json","paper":"https://pith.science/paper/WYQRPHGD"},"agent_actions":{"view_html":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW","download_json":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW.json","view_paper":"https://pith.science/paper/WYQRPHGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07289&json=true","fetch_graph":"https://pith.science/api/pith-number/WYQRPHGDM2KWPEVGBRSXRIIHBW/graph.json","fetch_events":"https://pith.science/api/pith-number/WYQRPHGDM2KWPEVGBRSXRIIHBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW/action/storage_attestation","attest_author":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW/action/author_attestation","sign_citation":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW/action/citation_signature","submit_replication":"https://pith.science/pith/WYQRPHGDM2KWPEVGBRSXRIIHBW/action/replication_record"}},"created_at":"2026-07-05T06:59:43.397921+00:00","updated_at":"2026-07-05T06:59:43.397921+00:00"}