{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N55JTMWDFAGXP6FZ35SODDDDJK","short_pith_number":"pith:N55JTMWD","schema_version":"1.0","canonical_sha256":"6f7a99b2c3280d77f8b9df64e18c634a9d78d3ab1bd1504cd7eebbc3f62cb7d9","source":{"kind":"arxiv","id":"2504.07100","version":1},"attestation_state":"computed","paper":{"title":"EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhay Gupta, Austen Liao, Jacob Cheung, Kevin Zhu, Philip Meng, Sean O'Brien, Shayan Sayyed","submitted_at":"2025-02-25T23:48:33Z","abstract_excerpt":"The diversity of human language, shaped by social, cultural, and regional influences, presents significant challenges for natural language processing (NLP) systems. Existing benchmarks often overlook intra-language variations, leaving speakers of non-standard dialects underserved. To address this gap, we introduce EnDive (English Diversity), a benchmark that evaluates five widely-used large language models (LLMs) across tasks in language understanding, algorithmic reasoning, mathematics, and logic. Our framework translates Standard American English datasets into five underrepresented dialects "},"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":"2504.07100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T23:48:33Z","cross_cats_sorted":[],"title_canon_sha256":"5e1b5c202048c24fce0739713f439af7edde023268cb865613b825f1b8cd5a29","abstract_canon_sha256":"4ae9e238c6eb4d147e7c679db8a2f2362813653014cd18e1925fc56014f5baa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:03.174388Z","signature_b64":"IWMKzQFZ+P4gwUUIDvb4qnmM1rprERQeJvCJoBmL8ZFKdZexXGeCDu/Jxma39P9PeG7/X6TD5XPtZp98mwIbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f7a99b2c3280d77f8b9df64e18c634a9d78d3ab1bd1504cd7eebbc3f62cb7d9","last_reissued_at":"2026-07-05T10:47:03.173885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:03.173885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhay Gupta, Austen Liao, Jacob Cheung, Kevin Zhu, Philip Meng, Sean O'Brien, Shayan Sayyed","submitted_at":"2025-02-25T23:48:33Z","abstract_excerpt":"The diversity of human language, shaped by social, cultural, and regional influences, presents significant challenges for natural language processing (NLP) systems. Existing benchmarks often overlook intra-language variations, leaving speakers of non-standard dialects underserved. To address this gap, we introduce EnDive (English Diversity), a benchmark that evaluates five widely-used large language models (LLMs) across tasks in language understanding, algorithmic reasoning, mathematics, and logic. Our framework translates Standard American English datasets into five underrepresented dialects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07100","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/2504.07100/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":"2504.07100","created_at":"2026-07-05T10:47:03.173943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07100v1","created_at":"2026-07-05T10:47:03.173943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07100","created_at":"2026-07-05T10:47:03.173943+00:00"},{"alias_kind":"pith_short_12","alias_value":"N55JTMWDFAGX","created_at":"2026-07-05T10:47:03.173943+00:00"},{"alias_kind":"pith_short_16","alias_value":"N55JTMWDFAGXP6FZ","created_at":"2026-07-05T10:47:03.173943+00:00"},{"alias_kind":"pith_short_8","alias_value":"N55JTMWD","created_at":"2026-07-05T10:47:03.173943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23824","citing_title":"Resource-Lean Lexicon Induction for German Dialects","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK","json":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK.json","graph_json":"https://pith.science/api/pith-number/N55JTMWDFAGXP6FZ35SODDDDJK/graph.json","events_json":"https://pith.science/api/pith-number/N55JTMWDFAGXP6FZ35SODDDDJK/events.json","paper":"https://pith.science/paper/N55JTMWD"},"agent_actions":{"view_html":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK","download_json":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK.json","view_paper":"https://pith.science/paper/N55JTMWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07100&json=true","fetch_graph":"https://pith.science/api/pith-number/N55JTMWDFAGXP6FZ35SODDDDJK/graph.json","fetch_events":"https://pith.science/api/pith-number/N55JTMWDFAGXP6FZ35SODDDDJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK/action/storage_attestation","attest_author":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK/action/author_attestation","sign_citation":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK/action/citation_signature","submit_replication":"https://pith.science/pith/N55JTMWDFAGXP6FZ35SODDDDJK/action/replication_record"}},"created_at":"2026-07-05T10:47:03.173943+00:00","updated_at":"2026-07-05T10:47:03.173943+00:00"}