{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZJOO4STR7D6TUXHR2DBJZQLZT","short_pith_number":"pith:AZJOO4ST","schema_version":"1.0","canonical_sha256":"0652e772538fc7e9d2e78e8614e60bccc469cd9378037f24339e3d24f5be9d58","source":{"kind":"arxiv","id":"2606.03219","version":1},"attestation_state":"computed","paper":{"title":"Sample-Size Scaling of the African Languages NLI Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anuj Tiwari, Hannah Nwokocha, Jesujuwon Egbewale, Oluwapelumi Ogunremu, Terry Oko-odion","submitted_at":"2026-06-02T06:27:16Z","abstract_excerpt":"African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief"},"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":"2606.03219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T06:27:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e28131c6e3471d4a785f2fa5c68e5a6974d311277072a3a2417b4b745b80aa6c","abstract_canon_sha256":"16c6f276f2a2374d20ed4f258e82658ea33a49fe8725e076cd2a30ca8db6bbb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:35.205721Z","signature_b64":"NJ9jaKrv/JIm3sxoyoiiz+Rj2aOO6oU4wm/MpjrjLKJtrQAyozvWTkrorV9jTIVg3IPPTnjzWXC8pK4Jaq6tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0652e772538fc7e9d2e78e8614e60bccc469cd9378037f24339e3d24f5be9d58","last_reissued_at":"2026-06-03T01:05:35.205296Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:35.205296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Size Scaling of the African Languages NLI Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anuj Tiwari, Hannah Nwokocha, Jesujuwon Egbewale, Oluwapelumi Ogunremu, Terry Oko-odion","submitted_at":"2026-06-02T06:27:16Z","abstract_excerpt":"African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance. The study is a systematic sample-size scaling study of natural language inference (NLI) on 16 African languages based on the AfriXNLI benchmark. Under controlled conditions, two multilingual transformer models with roughly 0.6B parameters XLM-R Large fine-tuned on XNLI and AfroXLM-R Large are tested on sample sizes of between 50 and 500 labeled examples and average their results across random subsampling runs. As opposed to the usual belief"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03219","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/2606.03219/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":"2606.03219","created_at":"2026-06-03T01:05:35.205366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03219v1","created_at":"2026-06-03T01:05:35.205366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03219","created_at":"2026-06-03T01:05:35.205366+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZJOO4STR7D6","created_at":"2026-06-03T01:05:35.205366+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZJOO4STR7D6TUXH","created_at":"2026-06-03T01:05:35.205366+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZJOO4ST","created_at":"2026-06-03T01:05:35.205366+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/AZJOO4STR7D6TUXHR2DBJZQLZT","json":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT.json","graph_json":"https://pith.science/api/pith-number/AZJOO4STR7D6TUXHR2DBJZQLZT/graph.json","events_json":"https://pith.science/api/pith-number/AZJOO4STR7D6TUXHR2DBJZQLZT/events.json","paper":"https://pith.science/paper/AZJOO4ST"},"agent_actions":{"view_html":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT","download_json":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT.json","view_paper":"https://pith.science/paper/AZJOO4ST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03219&json=true","fetch_graph":"https://pith.science/api/pith-number/AZJOO4STR7D6TUXHR2DBJZQLZT/graph.json","fetch_events":"https://pith.science/api/pith-number/AZJOO4STR7D6TUXHR2DBJZQLZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT/action/storage_attestation","attest_author":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT/action/author_attestation","sign_citation":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT/action/citation_signature","submit_replication":"https://pith.science/pith/AZJOO4STR7D6TUXHR2DBJZQLZT/action/replication_record"}},"created_at":"2026-06-03T01:05:35.205366+00:00","updated_at":"2026-06-03T01:05:35.205366+00:00"}