{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RVCGS3QR3PU64D5MGROBDCR2MP","short_pith_number":"pith:RVCGS3QR","schema_version":"1.0","canonical_sha256":"8d44696e11dbe9ee0fac345c118a3a63e6a375b689688f402a98e3d20dec489e","source":{"kind":"arxiv","id":"2409.11404","version":3},"attestation_state":"computed","paper":{"title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basel Mousi, Fahim Dalvi, Fatema Ahmad, Firoj Alam, Maram Hasanain, Md. Arid Hasan, Nadir Durrani, Shammur Absar Chowdhury, Tameem Kabbani","submitted_at":"2024-09-17T17:59:25Z","abstract_excerpt":"Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern Standard Arabic (MSA), created using Machine Translation (MT) combined with human post-editing. We present AraDiCE, a benchmark for Arabic Dialect and Cultural Evaluation. We evaluate LLMs on dialect comprehension and generation, focusing specifically on low-resource Arabic dialects. Additionally, we introduce the first-ever fine-grained benchmark designed to e"},"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":"2409.11404","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:59:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6b410bb099853d2241b8893c168bf46cc750e7ab3368687ff0239a7cf11271d","abstract_canon_sha256":"c6cb078cb23d410b9dec28215867111d6cb39311586d1f74825790599b180e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:52.061309Z","signature_b64":"ly5WZNiBedcjV5idViEnLhRAvl6LaYcTgpwxcwwA76VlptqYjz28LRCu6E2XH0iZKCS+y7C8kv7QwXNZzI5TAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d44696e11dbe9ee0fac345c118a3a63e6a375b689688f402a98e3d20dec489e","last_reissued_at":"2026-07-05T09:50:52.060791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:52.060791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basel Mousi, Fahim Dalvi, Fatema Ahmad, Firoj Alam, Maram Hasanain, Md. Arid Hasan, Nadir Durrani, Shammur Absar Chowdhury, Tameem Kabbani","submitted_at":"2024-09-17T17:59:25Z","abstract_excerpt":"Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern Standard Arabic (MSA), created using Machine Translation (MT) combined with human post-editing. We present AraDiCE, a benchmark for Arabic Dialect and Cultural Evaluation. We evaluate LLMs on dialect comprehension and generation, focusing specifically on low-resource Arabic dialects. Additionally, we introduce the first-ever fine-grained benchmark designed to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11404","kind":"arxiv","version":3},"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/2409.11404/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":"2409.11404","created_at":"2026-07-05T09:50:52.060853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11404v3","created_at":"2026-07-05T09:50:52.060853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11404","created_at":"2026-07-05T09:50:52.060853+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVCGS3QR3PU6","created_at":"2026-07-05T09:50:52.060853+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVCGS3QR3PU64D5M","created_at":"2026-07-05T09:50:52.060853+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVCGS3QR","created_at":"2026-07-05T09:50:52.060853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07617","citing_title":"Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP","json":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP.json","graph_json":"https://pith.science/api/pith-number/RVCGS3QR3PU64D5MGROBDCR2MP/graph.json","events_json":"https://pith.science/api/pith-number/RVCGS3QR3PU64D5MGROBDCR2MP/events.json","paper":"https://pith.science/paper/RVCGS3QR"},"agent_actions":{"view_html":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP","download_json":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP.json","view_paper":"https://pith.science/paper/RVCGS3QR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11404&json=true","fetch_graph":"https://pith.science/api/pith-number/RVCGS3QR3PU64D5MGROBDCR2MP/graph.json","fetch_events":"https://pith.science/api/pith-number/RVCGS3QR3PU64D5MGROBDCR2MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP/action/storage_attestation","attest_author":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP/action/author_attestation","sign_citation":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP/action/citation_signature","submit_replication":"https://pith.science/pith/RVCGS3QR3PU64D5MGROBDCR2MP/action/replication_record"}},"created_at":"2026-07-05T09:50:52.060853+00:00","updated_at":"2026-07-05T09:50:52.060853+00:00"}