{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VGSD73PVEQTHRM4OXGAO4WVUIH","short_pith_number":"pith:VGSD73PV","schema_version":"1.0","canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","source":{"kind":"arxiv","id":"1906.01265","version":3},"attestation_state":"computed","paper":{"title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Chujie Zheng, Minlie Huang","submitted_at":"2019-06-04T08:29:00Z","abstract_excerpt":"Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora. In this paper we propose a large-scale Chinese cloze test dataset ChID, which studies the comprehension of idiom, a unique language phenomenon in Chinese. In this corpus, the idioms in a passage are replaced by blank symbols and the correct answer needs to be chosen from well-designed candidate idioms. We carefully study how the design of candidate idioms and the representation of idioms affect the performance of state-of-the-art models. Results show that the machine accuracy is substantially wors"},"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":"1906.01265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T08:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"a90cb1a36f0158d4aa6b3771665f4ac369793ee3ba1df777886538bf27b69df3","abstract_canon_sha256":"26e1b239feb4e47113d381800ac52863cd829a83abce47ceb6d9c4d514253fd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:44.173276Z","signature_b64":"MgpeW5cAPqyL6J9dSUkKf07QCn1XLX8m6o6RL8tE7tRcie3P/d3eehqlfzcyyuQFJV5DBm1p6msGiP1j7bk8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a43fedf5242678b38eb980ee5ab441c9e2a447b7c6d3ac4a2a479e4c424300","last_reissued_at":"2026-07-05T00:35:44.172855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:44.172855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Chujie Zheng, Minlie Huang","submitted_at":"2019-06-04T08:29:00Z","abstract_excerpt":"Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora. In this paper we propose a large-scale Chinese cloze test dataset ChID, which studies the comprehension of idiom, a unique language phenomenon in Chinese. In this corpus, the idioms in a passage are replaced by blank symbols and the correct answer needs to be chosen from well-designed candidate idioms. We carefully study how the design of candidate idioms and the representation of idioms affect the performance of state-of-the-art models. Results show that the machine accuracy is substantially wors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01265","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/1906.01265/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":"1906.01265","created_at":"2026-07-05T00:35:44.172914+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01265v3","created_at":"2026-07-05T00:35:44.172914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01265","created_at":"2026-07-05T00:35:44.172914+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGSD73PVEQTH","created_at":"2026-07-05T00:35:44.172914+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGSD73PVEQTHRM4O","created_at":"2026-07-05T00:35:44.172914+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGSD73PV","created_at":"2026-07-05T00:35:44.172914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10421","citing_title":"Evaluating LLMs on Chinese Idiom Translation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH","json":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH.json","graph_json":"https://pith.science/api/pith-number/VGSD73PVEQTHRM4OXGAO4WVUIH/graph.json","events_json":"https://pith.science/api/pith-number/VGSD73PVEQTHRM4OXGAO4WVUIH/events.json","paper":"https://pith.science/paper/VGSD73PV"},"agent_actions":{"view_html":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH","download_json":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH.json","view_paper":"https://pith.science/paper/VGSD73PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01265&json=true","fetch_graph":"https://pith.science/api/pith-number/VGSD73PVEQTHRM4OXGAO4WVUIH/graph.json","fetch_events":"https://pith.science/api/pith-number/VGSD73PVEQTHRM4OXGAO4WVUIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/action/storage_attestation","attest_author":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/action/author_attestation","sign_citation":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/action/citation_signature","submit_replication":"https://pith.science/pith/VGSD73PVEQTHRM4OXGAO4WVUIH/action/replication_record"}},"created_at":"2026-07-05T00:35:44.172914+00:00","updated_at":"2026-07-05T00:35:44.172914+00:00"}