{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WFCXKXEIQSBGRE4MFMHX32DWY6","short_pith_number":"pith:WFCXKXEI","schema_version":"1.0","canonical_sha256":"b145755c88848268938c2b0f7de876c791e85e11f4c523a825b6fa81827fda9b","source":{"kind":"arxiv","id":"2401.17043","version":3},"attestation_state":"computed","paper":{"title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Enhong Chen, Feiyu Xiong, Hao Wu, Huanyong Liu, Simin Niu, Tong Xu, Wenjin Wang, Yuanjie Lyu, Zhiyu Li","submitted_at":"2024-01-30T14:25:32Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate \"hallucinated\" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they onl"},"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":"2401.17043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T14:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"78ce50568dedfe351372d9b2622a73dd93e54cbd860754324ae1c28a022f97ce","abstract_canon_sha256":"86a823ba7460399a22180ef04e2399882482ba4be6820c2b502101d710a81e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:52.936822Z","signature_b64":"n9/Dm9FzW9EYkxSdNbLA+yOoT9uaHMibgFYzMQKoZh1OTAuT+GiaPFAXD9BWLBjb3tRyxT7Ra70JGjAEZ5xSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b145755c88848268938c2b0f7de876c791e85e11f4c523a825b6fa81827fda9b","last_reissued_at":"2026-07-05T08:43:52.936382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:52.936382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Enhong Chen, Feiyu Xiong, Hao Wu, Huanyong Liu, Simin Niu, Tong Xu, Wenjin Wang, Yuanjie Lyu, Zhiyu Li","submitted_at":"2024-01-30T14:25:32Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate \"hallucinated\" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17043","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/2401.17043/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":"2401.17043","created_at":"2026-07-05T08:43:52.936447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17043v3","created_at":"2026-07-05T08:43:52.936447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17043","created_at":"2026-07-05T08:43:52.936447+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFCXKXEIQSBG","created_at":"2026-07-05T08:43:52.936447+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFCXKXEIQSBGRE4M","created_at":"2026-07-05T08:43:52.936447+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFCXKXEI","created_at":"2026-07-05T08:43:52.936447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05779","citing_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17943","citing_title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6","json":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6.json","graph_json":"https://pith.science/api/pith-number/WFCXKXEIQSBGRE4MFMHX32DWY6/graph.json","events_json":"https://pith.science/api/pith-number/WFCXKXEIQSBGRE4MFMHX32DWY6/events.json","paper":"https://pith.science/paper/WFCXKXEI"},"agent_actions":{"view_html":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6","download_json":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6.json","view_paper":"https://pith.science/paper/WFCXKXEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17043&json=true","fetch_graph":"https://pith.science/api/pith-number/WFCXKXEIQSBGRE4MFMHX32DWY6/graph.json","fetch_events":"https://pith.science/api/pith-number/WFCXKXEIQSBGRE4MFMHX32DWY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6/action/storage_attestation","attest_author":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6/action/author_attestation","sign_citation":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6/action/citation_signature","submit_replication":"https://pith.science/pith/WFCXKXEIQSBGRE4MFMHX32DWY6/action/replication_record"}},"created_at":"2026-07-05T08:43:52.936447+00:00","updated_at":"2026-07-05T08:43:52.936447+00:00"}