{"id":"W7077919379","doi":"10.48448/gt1h-8n75","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Arabic; Embedding; Benchmark (surveying); Suite; Field (mathematics); Language model; Natural language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008194091,0.0005009281,0.0004875968,0.0004074935,0.000832207,0.002223478,0.001189765,0.0003730127,0.00009669046],"category_scores_gemma":[0.0004485151,0.000428467,0.00004818204,0.0008199359,0.002639404,0.001065447,0.001566346,0.000490204,0.000003568209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005521875,"about_ca_system_score_gemma":0.0004546325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000211479,"about_ca_topic_score_gemma":0.00003976839,"domain_scores_codex":[0.9965403,0.00004392334,0.0004157033,0.001658155,0.0005312811,0.0008106244],"domain_scores_gemma":[0.9981863,0.0001658199,0.0002904822,0.0006520194,0.0003751813,0.0003301779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001372237,0.0009587477,0.05025905,0.00543922,0.0006505796,0.0008778473,0.01022237,0.0253082,0.006906973,0.440025,0.1028862,0.3563286],"study_design_scores_gemma":[0.001635095,0.0001544495,0.001688046,0.0008001967,0.00005312034,0.0002834398,0.0002191114,0.8694206,0.001273164,0.04827286,0.07427118,0.00192866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03223467,0.009500303,0.1039605,0.002369083,0.002057406,0.00117118,0.00009758174,0.0008955976,0.8477136],"genre_scores_gemma":[0.7607903,0.001605543,0.02280396,0.0007012038,0.000468714,0.00002864514,0.00005383584,0.00004806785,0.2134997],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8441125,"threshold_uncertainty_score":0.9998167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01905219705620825,"score_gpt":0.320158114463073,"score_spread":0.3011059174068648,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}