{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z2O6724XXX5EUBKPPVEWD4OUM7","short_pith_number":"pith:Z2O6724X","schema_version":"1.0","canonical_sha256":"ce9defeb97bdfa4a054f7d4961f1d467d5368cb90bdcadf84aee5828db85e21c","source":{"kind":"arxiv","id":"2402.19248","version":2},"attestation_state":"computed","paper":{"title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boli Chen, Fei Huang, Hai-Tao Zheng, Pengjun Xie, Ruixue Ding, Wenlian Lu, Xinyu Wang, Yinghui Li, Yong Jiang, Zhikun Xu","submitted_at":"2024-02-29T15:22:13Z","abstract_excerpt":"How to better evaluate the capabilities of Large Language Models (LLMs) is the focal point and hot topic in current LLMs research. Previous work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer the latest dynamic questions well. To promote the improvement of Chinese LLMs' ability to answer dynamic questions, in this paper, we introduce CDQA, a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest news on the Chinese Internet. We obtain high-quality data through a pipeline that combines humans and models, a"},"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":"2402.19248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T15:22:13Z","cross_cats_sorted":[],"title_canon_sha256":"b6a3f823d1061b96e58c4561e5384c4bb608290a1e4d470cae5cc9369a8440e6","abstract_canon_sha256":"1df0638c5b90d9914bf1d785dbedd3968cf8d4bd8fde354989d0d26fcd1e8f0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:11.398714Z","signature_b64":"BSjrC1Y3cEFvELqe9jglXykd9pI2WtlsNgvMCJnHh3dhmb9OUnZvK8n5BENbBpz5OQpnPckiIRPfs1ekA+PICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce9defeb97bdfa4a054f7d4961f1d467d5368cb90bdcadf84aee5828db85e21c","last_reissued_at":"2026-07-05T07:51:11.398240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:11.398240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boli Chen, Fei Huang, Hai-Tao Zheng, Pengjun Xie, Ruixue Ding, Wenlian Lu, Xinyu Wang, Yinghui Li, Yong Jiang, Zhikun Xu","submitted_at":"2024-02-29T15:22:13Z","abstract_excerpt":"How to better evaluate the capabilities of Large Language Models (LLMs) is the focal point and hot topic in current LLMs research. Previous work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer the latest dynamic questions well. To promote the improvement of Chinese LLMs' ability to answer dynamic questions, in this paper, we introduce CDQA, a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest news on the Chinese Internet. We obtain high-quality data through a pipeline that combines humans and models, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19248","kind":"arxiv","version":2},"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/2402.19248/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":"2402.19248","created_at":"2026-07-05T07:51:11.398289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19248v2","created_at":"2026-07-05T07:51:11.398289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19248","created_at":"2026-07-05T07:51:11.398289+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2O6724XXX5E","created_at":"2026-07-05T07:51:11.398289+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2O6724XXX5EUBKP","created_at":"2026-07-05T07:51:11.398289+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2O6724X","created_at":"2026-07-05T07:51:11.398289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.19314","citing_title":"BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7","json":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7.json","graph_json":"https://pith.science/api/pith-number/Z2O6724XXX5EUBKPPVEWD4OUM7/graph.json","events_json":"https://pith.science/api/pith-number/Z2O6724XXX5EUBKPPVEWD4OUM7/events.json","paper":"https://pith.science/paper/Z2O6724X"},"agent_actions":{"view_html":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7","download_json":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7.json","view_paper":"https://pith.science/paper/Z2O6724X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19248&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2O6724XXX5EUBKPPVEWD4OUM7/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2O6724XXX5EUBKPPVEWD4OUM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7/action/storage_attestation","attest_author":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7/action/author_attestation","sign_citation":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7/action/citation_signature","submit_replication":"https://pith.science/pith/Z2O6724XXX5EUBKPPVEWD4OUM7/action/replication_record"}},"created_at":"2026-07-05T07:51:11.398289+00:00","updated_at":"2026-07-05T07:51:11.398289+00:00"}