{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YMEMQISPLRRBQGW4U5VV67AIXE","short_pith_number":"pith:YMEMQISP","schema_version":"1.0","canonical_sha256":"c308c8224f5c62181adca76b5f7c08b93dac6db243c498244100fca416d0537b","source":{"kind":"arxiv","id":"2002.06071","version":2},"attestation_state":"computed","paper":{"title":"FQuAD: French Question Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Martin d'Hoffschmidt, Maxime Vidal, Quentin Heinrich, Tom Brendl\\'e, Wacim Belblidia","submitted_at":"2020-02-14T15:23:38Z","abstract_excerpt":"Recent advances in the field of language modeling have improved state-of-the-art results on many Natural Language Processing tasks. Among them, Reading Comprehension has made significant progress over the past few years. However, most results are reported in English since labeled resources available in other languages, such as French, remain scarce. In the present work, we introduce the French Question Answering Dataset (FQuAD). FQuAD is a French Native Reading Comprehension dataset of questions and answers on a set of Wikipedia articles that consists of 25,000+ samples for the 1.0 version and"},"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":"2002.06071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T15:23:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c8a2caeddb81b12ea00c2ebc192b90ee870de11f598829b4ebd118ab152cb0da","abstract_canon_sha256":"f1c1abd676f56f234c350f8ae10fcecf5f900f1061a1615d5f9e962d84fa757c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:26.167531Z","signature_b64":"qVxTpVorWqH+XEc7ZSw8lrRy1Rg81eXgD0Nd/8jZWuZoMJj4R/kUQEKJs3AOcnw5TsRwA4yhIc1iIjfKZ/CYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c308c8224f5c62181adca76b5f7c08b93dac6db243c498244100fca416d0537b","last_reissued_at":"2026-07-05T01:05:26.167098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:26.167098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FQuAD: French Question Answering Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Martin d'Hoffschmidt, Maxime Vidal, Quentin Heinrich, Tom Brendl\\'e, Wacim Belblidia","submitted_at":"2020-02-14T15:23:38Z","abstract_excerpt":"Recent advances in the field of language modeling have improved state-of-the-art results on many Natural Language Processing tasks. Among them, Reading Comprehension has made significant progress over the past few years. However, most results are reported in English since labeled resources available in other languages, such as French, remain scarce. In the present work, we introduce the French Question Answering Dataset (FQuAD). FQuAD is a French Native Reading Comprehension dataset of questions and answers on a set of Wikipedia articles that consists of 25,000+ samples for the 1.0 version and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06071","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/2002.06071/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":"2002.06071","created_at":"2026-07-05T01:05:26.167153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06071v2","created_at":"2026-07-05T01:05:26.167153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06071","created_at":"2026-07-05T01:05:26.167153+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMEMQISPLRRB","created_at":"2026-07-05T01:05:26.167153+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMEMQISPLRRBQGW4","created_at":"2026-07-05T01:05:26.167153+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMEMQISP","created_at":"2026-07-05T01:05:26.167153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20920","citing_title":"FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE","json":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE.json","graph_json":"https://pith.science/api/pith-number/YMEMQISPLRRBQGW4U5VV67AIXE/graph.json","events_json":"https://pith.science/api/pith-number/YMEMQISPLRRBQGW4U5VV67AIXE/events.json","paper":"https://pith.science/paper/YMEMQISP"},"agent_actions":{"view_html":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE","download_json":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE.json","view_paper":"https://pith.science/paper/YMEMQISP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06071&json=true","fetch_graph":"https://pith.science/api/pith-number/YMEMQISPLRRBQGW4U5VV67AIXE/graph.json","fetch_events":"https://pith.science/api/pith-number/YMEMQISPLRRBQGW4U5VV67AIXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE/action/storage_attestation","attest_author":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE/action/author_attestation","sign_citation":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE/action/citation_signature","submit_replication":"https://pith.science/pith/YMEMQISPLRRBQGW4U5VV67AIXE/action/replication_record"}},"created_at":"2026-07-05T01:05:26.167153+00:00","updated_at":"2026-07-05T01:05:26.167153+00:00"}