{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PQTGRQEVJ4QS3FL3LNPKZKBXQA","short_pith_number":"pith:PQTGRQEV","schema_version":"1.0","canonical_sha256":"7c2668c0954f212d957b5b5eaca83780028adf5b0bec5289a2827d8be85bb74e","source":{"kind":"arxiv","id":"2111.06086","version":1},"attestation_state":"computed","paper":{"title":"A Chinese Multi-type Complex Questions Answering Dataset over Wikidata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Fengqing Jiang, Jianyun Zou, Lichao Zhang, Min Yang, Qifan Pan, Ran Qin, Shushu Wang, Songfang Huang, Yechen Xu, Yifan He, Zhou Zhao","submitted_at":"2021-11-11T07:39:16Z","abstract_excerpt":"Complex Knowledge Base Question Answering is a popular area of research in the past decade. Recent public datasets have led to encouraging results in this field, but are mostly limited to English and only involve a small number of question types and relations, hindering research in more realistic settings and in languages other than English. In addition, few state-of-the-art KBQA models are trained on Wikidata, one of the most popular real-world knowledge bases. We propose CLC-QuAD, the first large scale complex Chinese semantic parsing dataset over Wikidata to address these challenges. Togeth"},"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":"2111.06086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-11T07:39:16Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"0fcba5c80c3d5855be1a1ee96a3241e82161306bc00edd2235ca999837d9471e","abstract_canon_sha256":"e16a1cf55df1b3163cdfe4fb920b1a9a57b1827ebc1f8c4e96c680665727e494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:57.945533Z","signature_b64":"sGcKDmn4cfmXlCOFhAHK43YTSfH6+kgQO9gY72QTGdkWzI3aWj3wllzWbXosmhXMWnJGfCrYr52/Jf9u2PPxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c2668c0954f212d957b5b5eaca83780028adf5b0bec5289a2827d8be85bb74e","last_reissued_at":"2026-07-05T03:30:57.945124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:57.945124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Chinese Multi-type Complex Questions Answering Dataset over Wikidata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Fengqing Jiang, Jianyun Zou, Lichao Zhang, Min Yang, Qifan Pan, Ran Qin, Shushu Wang, Songfang Huang, Yechen Xu, Yifan He, Zhou Zhao","submitted_at":"2021-11-11T07:39:16Z","abstract_excerpt":"Complex Knowledge Base Question Answering is a popular area of research in the past decade. Recent public datasets have led to encouraging results in this field, but are mostly limited to English and only involve a small number of question types and relations, hindering research in more realistic settings and in languages other than English. In addition, few state-of-the-art KBQA models are trained on Wikidata, one of the most popular real-world knowledge bases. We propose CLC-QuAD, the first large scale complex Chinese semantic parsing dataset over Wikidata to address these challenges. Togeth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06086","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/2111.06086/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":"2111.06086","created_at":"2026-07-05T03:30:57.945182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06086v1","created_at":"2026-07-05T03:30:57.945182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06086","created_at":"2026-07-05T03:30:57.945182+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQTGRQEVJ4QS","created_at":"2026-07-05T03:30:57.945182+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQTGRQEVJ4QS3FL3","created_at":"2026-07-05T03:30:57.945182+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQTGRQEV","created_at":"2026-07-05T03:30:57.945182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19971","citing_title":"Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA","json":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA.json","graph_json":"https://pith.science/api/pith-number/PQTGRQEVJ4QS3FL3LNPKZKBXQA/graph.json","events_json":"https://pith.science/api/pith-number/PQTGRQEVJ4QS3FL3LNPKZKBXQA/events.json","paper":"https://pith.science/paper/PQTGRQEV"},"agent_actions":{"view_html":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA","download_json":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA.json","view_paper":"https://pith.science/paper/PQTGRQEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06086&json=true","fetch_graph":"https://pith.science/api/pith-number/PQTGRQEVJ4QS3FL3LNPKZKBXQA/graph.json","fetch_events":"https://pith.science/api/pith-number/PQTGRQEVJ4QS3FL3LNPKZKBXQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA/action/storage_attestation","attest_author":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA/action/author_attestation","sign_citation":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA/action/citation_signature","submit_replication":"https://pith.science/pith/PQTGRQEVJ4QS3FL3LNPKZKBXQA/action/replication_record"}},"created_at":"2026-07-05T03:30:57.945182+00:00","updated_at":"2026-07-05T03:30:57.945182+00:00"}