{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JPBGYMECQDEDKP7BP2R2SOWBDM","short_pith_number":"pith:JPBGYMEC","schema_version":"1.0","canonical_sha256":"4bc26c308280c8353fe17ea3a93ac11b01f9daa62a6f142dc102d212c0db3303","source":{"kind":"arxiv","id":"2412.04193","version":2},"attestation_state":"computed","paper":{"title":"AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kelly Marchisio, Nathaniel R. Robinson, Sebastian Ruder, Shahd Abdelmoneim","submitted_at":"2024-12-05T14:33:00Z","abstract_excerpt":"Dialectal Arabic (DA) varieties are under-served by language technologies, particularly large language models (LLMs). This trend threatens to exacerbate existing social inequalities and limits LLM applications, yet the research community lacks operationalized performance measurements in DA. We present a framework that comprehensively assesses LLMs' DA modeling capabilities across four dimensions: fidelity, understanding, quality, and diglossia. We evaluate nine LLMs in eight DA varieties and provide practical recommendations. Our evaluation suggests that LLMs do not produce DA as well as they "},"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":"2412.04193","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T14:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"d9c64baec4dcddc0283adc9f0c9c5c16e6ddd57c8ff632e48d98a0ad8292b14d","abstract_canon_sha256":"a67f3faf24e46f8ff2836144fc91b823d968bea3966f5097653ec88c6b810db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:57.447917Z","signature_b64":"yAHXGc/vhEGiFdz4AojWzmQiosUDnPSq7Vgynx8zZ0AFI2Sq2sOAYt+P1h3zHS2U1eTBqHJFLBi/tN9/6eHYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc26c308280c8353fe17ea3a93ac11b01f9daa62a6f142dc102d212c0db3303","last_reissued_at":"2026-07-05T09:56:57.447501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:57.447501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kelly Marchisio, Nathaniel R. Robinson, Sebastian Ruder, Shahd Abdelmoneim","submitted_at":"2024-12-05T14:33:00Z","abstract_excerpt":"Dialectal Arabic (DA) varieties are under-served by language technologies, particularly large language models (LLMs). This trend threatens to exacerbate existing social inequalities and limits LLM applications, yet the research community lacks operationalized performance measurements in DA. We present a framework that comprehensively assesses LLMs' DA modeling capabilities across four dimensions: fidelity, understanding, quality, and diglossia. We evaluate nine LLMs in eight DA varieties and provide practical recommendations. Our evaluation suggests that LLMs do not produce DA as well as they "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04193","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/2412.04193/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":"2412.04193","created_at":"2026-07-05T09:56:57.447557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04193v2","created_at":"2026-07-05T09:56:57.447557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04193","created_at":"2026-07-05T09:56:57.447557+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPBGYMECQDED","created_at":"2026-07-05T09:56:57.447557+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPBGYMECQDEDKP7B","created_at":"2026-07-05T09:56:57.447557+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPBGYMEC","created_at":"2026-07-05T09:56:57.447557+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/JPBGYMECQDEDKP7BP2R2SOWBDM","json":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM.json","graph_json":"https://pith.science/api/pith-number/JPBGYMECQDEDKP7BP2R2SOWBDM/graph.json","events_json":"https://pith.science/api/pith-number/JPBGYMECQDEDKP7BP2R2SOWBDM/events.json","paper":"https://pith.science/paper/JPBGYMEC"},"agent_actions":{"view_html":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM","download_json":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM.json","view_paper":"https://pith.science/paper/JPBGYMEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04193&json=true","fetch_graph":"https://pith.science/api/pith-number/JPBGYMECQDEDKP7BP2R2SOWBDM/graph.json","fetch_events":"https://pith.science/api/pith-number/JPBGYMECQDEDKP7BP2R2SOWBDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM/action/storage_attestation","attest_author":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM/action/author_attestation","sign_citation":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM/action/citation_signature","submit_replication":"https://pith.science/pith/JPBGYMECQDEDKP7BP2R2SOWBDM/action/replication_record"}},"created_at":"2026-07-05T09:56:57.447557+00:00","updated_at":"2026-07-05T09:56:57.447557+00:00"}