{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MCJMLIPQTO6IARZOZI7GCMVDXE","short_pith_number":"pith:MCJMLIPQ","schema_version":"1.0","canonical_sha256":"6092c5a1f09bbc80472eca3e6132a3b9083da032ad857e5f8b8fe82e19f2e8a2","source":{"kind":"arxiv","id":"1909.07005","version":2},"attestation_state":"computed","paper":{"title":"KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jooyoul Lee, Myungji Kim, Seungyoung Lim","submitted_at":"2019-09-16T06:15:27Z","abstract_excerpt":"Machine Reading Comprehension (MRC) is a task that requires machine to understand natural language and answer questions by reading a document. It is the core of automatic response technology such as chatbots and automatized customer supporting systems. We present Korean Question Answering Dataset(KorQuAD), a large-scale Korean dataset for extractive machine reading comprehension task. It consists of 70,000+ human generated question-answer pairs on Korean Wikipedia articles. We release KorQuAD1.0 and launch a challenge at https://KorQuAD.github.io to encourage the development of multilingual na"},"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":"1909.07005","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-16T06:15:27Z","cross_cats_sorted":[],"title_canon_sha256":"1d9f5c3dddc0c936068f350dae0d01f5ce329a49f9815a8ebe002d32ef0fb21f","abstract_canon_sha256":"7c00fce01d91b7c702a9f091cff68df983607399a23a05f76f9279d40b9c1f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:56.973478Z","signature_b64":"i60ompcN/qLMAcrS5Ssxk/80oqe/lYBjighxYo8daAE3A/1jogrpaWPSnU2070XeZb3exXE3S9M7nSfzQXiVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6092c5a1f09bbc80472eca3e6132a3b9083da032ad857e5f8b8fe82e19f2e8a2","last_reissued_at":"2026-07-05T00:04:56.973030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:56.973030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jooyoul Lee, Myungji Kim, Seungyoung Lim","submitted_at":"2019-09-16T06:15:27Z","abstract_excerpt":"Machine Reading Comprehension (MRC) is a task that requires machine to understand natural language and answer questions by reading a document. It is the core of automatic response technology such as chatbots and automatized customer supporting systems. We present Korean Question Answering Dataset(KorQuAD), a large-scale Korean dataset for extractive machine reading comprehension task. It consists of 70,000+ human generated question-answer pairs on Korean Wikipedia articles. We release KorQuAD1.0 and launch a challenge at https://KorQuAD.github.io to encourage the development of multilingual na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07005","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/1909.07005/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":"1909.07005","created_at":"2026-07-05T00:04:56.973085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07005v2","created_at":"2026-07-05T00:04:56.973085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07005","created_at":"2026-07-05T00:04:56.973085+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCJMLIPQTO6I","created_at":"2026-07-05T00:04:56.973085+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCJMLIPQTO6IARZO","created_at":"2026-07-05T00:04:56.973085+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCJMLIPQ","created_at":"2026-07-05T00:04:56.973085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27595","citing_title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17443","citing_title":"Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17443","citing_title":"Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23948","citing_title":"KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE","json":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE.json","graph_json":"https://pith.science/api/pith-number/MCJMLIPQTO6IARZOZI7GCMVDXE/graph.json","events_json":"https://pith.science/api/pith-number/MCJMLIPQTO6IARZOZI7GCMVDXE/events.json","paper":"https://pith.science/paper/MCJMLIPQ"},"agent_actions":{"view_html":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE","download_json":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE.json","view_paper":"https://pith.science/paper/MCJMLIPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07005&json=true","fetch_graph":"https://pith.science/api/pith-number/MCJMLIPQTO6IARZOZI7GCMVDXE/graph.json","fetch_events":"https://pith.science/api/pith-number/MCJMLIPQTO6IARZOZI7GCMVDXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE/action/storage_attestation","attest_author":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE/action/author_attestation","sign_citation":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE/action/citation_signature","submit_replication":"https://pith.science/pith/MCJMLIPQTO6IARZOZI7GCMVDXE/action/replication_record"}},"created_at":"2026-07-05T00:04:56.973085+00:00","updated_at":"2026-07-05T00:04:56.973085+00:00"}