{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUKYMHNU6LC7DWQ4YLESQ3PCQP","short_pith_number":"pith:KUKYMHNU","schema_version":"1.0","canonical_sha256":"5515861db4f2c5f1da1cc2c9286de283cace6f16a13640029c678c7b2224db09","source":{"kind":"arxiv","id":"2404.09163","version":1},"attestation_state":"computed","paper":{"title":"GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amani Namboori, Andy Rosenbaum, Saleh Soltan, Shivam Mangale","submitted_at":"2024-04-14T06:55:42Z","abstract_excerpt":"The emergence of Large Language Models (LLMs) with capabilities like In-Context Learning (ICL) has ushered in new possibilities for data generation across various domains while minimizing the need for extensive data collection and modeling techniques. Researchers have explored ways to use this generated synthetic data to optimize smaller student models for reduced deployment costs and lower latency in downstream tasks. However, ICL-generated data often suffers from low quality as the task specificity is limited with few examples used in ICL. In this paper, we propose GeMQuAD - a semi-supervise"},"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":"2404.09163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T06:55:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a4bd0a4a7f023e9ff3624fb6ee73f0f685390aa6b3890b0d9b637e05b646566","abstract_canon_sha256":"6ae8c2d68fed193d426023662748dbda8410236119baf0749a0d230aed83097d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:45.959799Z","signature_b64":"PIBLvju8IRNUqnqZAH+F2R52V7LREp4uYd/c14ne8MLyC43JVJsBPV/8J3F67IxbNczmH39D9PRVYQ9QxNvVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5515861db4f2c5f1da1cc2c9286de283cace6f16a13640029c678c7b2224db09","last_reissued_at":"2026-07-05T08:07:45.959330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:45.959330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amani Namboori, Andy Rosenbaum, Saleh Soltan, Shivam Mangale","submitted_at":"2024-04-14T06:55:42Z","abstract_excerpt":"The emergence of Large Language Models (LLMs) with capabilities like In-Context Learning (ICL) has ushered in new possibilities for data generation across various domains while minimizing the need for extensive data collection and modeling techniques. Researchers have explored ways to use this generated synthetic data to optimize smaller student models for reduced deployment costs and lower latency in downstream tasks. However, ICL-generated data often suffers from low quality as the task specificity is limited with few examples used in ICL. In this paper, we propose GeMQuAD - a semi-supervise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09163","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/2404.09163/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":"2404.09163","created_at":"2026-07-05T08:07:45.959391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09163v1","created_at":"2026-07-05T08:07:45.959391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09163","created_at":"2026-07-05T08:07:45.959391+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUKYMHNU6LC7","created_at":"2026-07-05T08:07:45.959391+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUKYMHNU6LC7DWQ4","created_at":"2026-07-05T08:07:45.959391+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUKYMHNU","created_at":"2026-07-05T08:07:45.959391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26048","citing_title":"BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP","json":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP.json","graph_json":"https://pith.science/api/pith-number/KUKYMHNU6LC7DWQ4YLESQ3PCQP/graph.json","events_json":"https://pith.science/api/pith-number/KUKYMHNU6LC7DWQ4YLESQ3PCQP/events.json","paper":"https://pith.science/paper/KUKYMHNU"},"agent_actions":{"view_html":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP","download_json":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP.json","view_paper":"https://pith.science/paper/KUKYMHNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09163&json=true","fetch_graph":"https://pith.science/api/pith-number/KUKYMHNU6LC7DWQ4YLESQ3PCQP/graph.json","fetch_events":"https://pith.science/api/pith-number/KUKYMHNU6LC7DWQ4YLESQ3PCQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP/action/storage_attestation","attest_author":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP/action/author_attestation","sign_citation":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP/action/citation_signature","submit_replication":"https://pith.science/pith/KUKYMHNU6LC7DWQ4YLESQ3PCQP/action/replication_record"}},"created_at":"2026-07-05T08:07:45.959391+00:00","updated_at":"2026-07-05T08:07:45.959391+00:00"}