{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z4MMCVHBS4NCQUNSCTO63OCIEU","short_pith_number":"pith:Z4MMCVHB","schema_version":"1.0","canonical_sha256":"cf18c154e1971a2851b214ddedb848252d1a8a3f3f2da29d42e75ae8ecb04b57","source":{"kind":"arxiv","id":"2502.07642","version":1},"attestation_state":"computed","paper":{"title":"FoQA: A Faroese Question-Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Annika Simonsen, Dan Saattrup Nielsen, Hafsteinn Einarsson","submitted_at":"2025-02-11T15:33:17Z","abstract_excerpt":"We present FoQA, a Faroese extractive question-answering (QA) dataset with 2,000 samples, created using a semi-automated approach combining Large Language Models (LLMs) and human validation. The dataset was generated from Faroese Wikipedia articles using GPT-4-turbo for initial QA generation, followed by question rephrasing to increase complexity and native speaker validation to ensure quality. We provide baseline performance metrics for FoQA across multiple models, including LLMs and BERT, demonstrating its effectiveness in evaluating Faroese QA performance. The dataset is released in three v"},"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":"2502.07642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T15:33:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7d5632f83859f6323660cd7c2bd25d76db7cf4a31341a94424a02c71b42e5d0","abstract_canon_sha256":"77478355d44228977609187eaeeaf8f2f257fff564a5ed6bb0925d7ee2eb6631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:40.445359Z","signature_b64":"ccr83BJsVntv9ij/QQJITPRFHzMSVSINcHcVo2u2yai+IvQL3gf4DTMhsleqs3z4XySPbKCufrnvsxP4225JAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf18c154e1971a2851b214ddedb848252d1a8a3f3f2da29d42e75ae8ecb04b57","last_reissued_at":"2026-07-05T10:12:40.444807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:40.444807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoQA: A Faroese Question-Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Annika Simonsen, Dan Saattrup Nielsen, Hafsteinn Einarsson","submitted_at":"2025-02-11T15:33:17Z","abstract_excerpt":"We present FoQA, a Faroese extractive question-answering (QA) dataset with 2,000 samples, created using a semi-automated approach combining Large Language Models (LLMs) and human validation. The dataset was generated from Faroese Wikipedia articles using GPT-4-turbo for initial QA generation, followed by question rephrasing to increase complexity and native speaker validation to ensure quality. We provide baseline performance metrics for FoQA across multiple models, including LLMs and BERT, demonstrating its effectiveness in evaluating Faroese QA performance. The dataset is released in three v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07642","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/2502.07642/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":"2502.07642","created_at":"2026-07-05T10:12:40.444872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07642v1","created_at":"2026-07-05T10:12:40.444872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07642","created_at":"2026-07-05T10:12:40.444872+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4MMCVHBS4NC","created_at":"2026-07-05T10:12:40.444872+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4MMCVHBS4NCQUNS","created_at":"2026-07-05T10:12:40.444872+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4MMCVHB","created_at":"2026-07-05T10:12:40.444872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU","json":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU.json","graph_json":"https://pith.science/api/pith-number/Z4MMCVHBS4NCQUNSCTO63OCIEU/graph.json","events_json":"https://pith.science/api/pith-number/Z4MMCVHBS4NCQUNSCTO63OCIEU/events.json","paper":"https://pith.science/paper/Z4MMCVHB"},"agent_actions":{"view_html":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU","download_json":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU.json","view_paper":"https://pith.science/paper/Z4MMCVHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07642&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4MMCVHBS4NCQUNSCTO63OCIEU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4MMCVHBS4NCQUNSCTO63OCIEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU/action/storage_attestation","attest_author":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU/action/author_attestation","sign_citation":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU/action/citation_signature","submit_replication":"https://pith.science/pith/Z4MMCVHBS4NCQUNSCTO63OCIEU/action/replication_record"}},"created_at":"2026-07-05T10:12:40.444872+00:00","updated_at":"2026-07-05T10:12:40.444872+00:00"}