{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JO4LSOYFKSQWBQYODYB7GOZPUZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e07ed782acb429f6d8ba8f50f10d5ff6e69112bf41b1352f89a08f7da5a48d70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T20:18:36Z","title_canon_sha256":"f748f8b787a7ab48e7d3c5325e829add816603e2c3a06726a09fdbde3e1fb416"},"schema_version":"1.0","source":{"id":"2403.11009","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11009","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11009v2","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11009","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"JO4LSOYFKSQW","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"JO4LSOYFKSQWBQYO","created_at":"2026-07-05T08:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"JO4LSOYF","created_at":"2026-07-05T08:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:154e535d477c39e7d4bc0f35afd28032f951175254fecfaf2b1452b10200ed6a","target":"graph","created_at":"2026-07-05T08:41:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.11009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aarohi Srivastava, Antonios Anastasopoulos, David Chiang, Fahim Faisal, Kabir Ahuja, Orevaoghene Ahia, Yulia Tsvetkov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T20:18:36Z","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11009","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4da1a8b2c17c44e9553715b02bf00750db649c625d092f13b85911f39a981de8","target":"record","created_at":"2026-07-05T08:41:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e07ed782acb429f6d8ba8f50f10d5ff6e69112bf41b1352f89a08f7da5a48d70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T20:18:36Z","title_canon_sha256":"f748f8b787a7ab48e7d3c5325e829add816603e2c3a06726a09fdbde3e1fb416"},"schema_version":"1.0","source":{"id":"2403.11009","kind":"arxiv","version":2}},"canonical_sha256":"4bb8b93b0554a160c30e1e03f33b2fa6668999f39675c895e9503cf8def3db83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bb8b93b0554a160c30e1e03f33b2fa6668999f39675c895e9503cf8def3db83","first_computed_at":"2026-07-05T08:41:00.975291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:00.975291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nRYLezOgrN33JQ+GM49kI/t/L7+SpgBM/mumngVLbZ6UaywSp3vFpxJbU1c+i6qFbu83SH70oheBI5hcJrKlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:00.975799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11009","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4da1a8b2c17c44e9553715b02bf00750db649c625d092f13b85911f39a981de8","sha256:154e535d477c39e7d4bc0f35afd28032f951175254fecfaf2b1452b10200ed6a"],"state_sha256":"b1bec5406ebb0593eba20723dca5b741f26e702235b33fa017f26011a018d952"}