{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JO4LSOYFKSQWBQYODYB7GOZPUZ","short_pith_number":"pith:JO4LSOYF","schema_version":"1.0","canonical_sha256":"4bb8b93b0554a160c30e1e03f33b2fa6668999f39675c895e9503cf8def3db83","source":{"kind":"arxiv","id":"2403.11009","version":2},"attestation_state":"computed","paper":{"title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aarohi Srivastava, Antonios Anastasopoulos, David Chiang, Fahim Faisal, Kabir Ahuja, Orevaoghene Ahia, Yulia Tsvetkov","submitted_at":"2024-03-16T20:18:36Z","abstract_excerpt":"Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of"},"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":"2403.11009","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T20:18:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f748f8b787a7ab48e7d3c5325e829add816603e2c3a06726a09fdbde3e1fb416","abstract_canon_sha256":"e07ed782acb429f6d8ba8f50f10d5ff6e69112bf41b1352f89a08f7da5a48d70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:00.975799Z","signature_b64":"nRYLezOgrN33JQ+GM49kI/t/L7+SpgBM/mumngVLbZ6UaywSp3vFpxJbU1c+i6qFbu83SH70oheBI5hcJrKlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb8b93b0554a160c30e1e03f33b2fa6668999f39675c895e9503cf8def3db83","last_reissued_at":"2026-07-05T08:41:00.975291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:00.975291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aarohi Srivastava, Antonios Anastasopoulos, David Chiang, Fahim Faisal, Kabir Ahuja, Orevaoghene Ahia, Yulia Tsvetkov","submitted_at":"2024-03-16T20:18:36Z","abstract_excerpt":"Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11009","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/2403.11009/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":"2403.11009","created_at":"2026-07-05T08:41:00.975365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11009v2","created_at":"2026-07-05T08:41:00.975365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11009","created_at":"2026-07-05T08:41:00.975365+00:00"},{"alias_kind":"pith_short_12","alias_value":"JO4LSOYFKSQW","created_at":"2026-07-05T08:41:00.975365+00:00"},{"alias_kind":"pith_short_16","alias_value":"JO4LSOYFKSQWBQYO","created_at":"2026-07-05T08:41:00.975365+00:00"},{"alias_kind":"pith_short_8","alias_value":"JO4LSOYF","created_at":"2026-07-05T08:41:00.975365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04497","citing_title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ","json":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ.json","graph_json":"https://pith.science/api/pith-number/JO4LSOYFKSQWBQYODYB7GOZPUZ/graph.json","events_json":"https://pith.science/api/pith-number/JO4LSOYFKSQWBQYODYB7GOZPUZ/events.json","paper":"https://pith.science/paper/JO4LSOYF"},"agent_actions":{"view_html":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ","download_json":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ.json","view_paper":"https://pith.science/paper/JO4LSOYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11009&json=true","fetch_graph":"https://pith.science/api/pith-number/JO4LSOYFKSQWBQYODYB7GOZPUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JO4LSOYFKSQWBQYODYB7GOZPUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ/action/storage_attestation","attest_author":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ/action/author_attestation","sign_citation":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ/action/citation_signature","submit_replication":"https://pith.science/pith/JO4LSOYFKSQWBQYODYB7GOZPUZ/action/replication_record"}},"created_at":"2026-07-05T08:41:00.975365+00:00","updated_at":"2026-07-05T08:41:00.975365+00:00"}