{"id":"W4385573558","doi":"10.18653/v1/2022.wanlp-1.7","title":"A Benchmark Study of Contrastive Learning for Arabic Social Meaning","year":2022,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Meaning (existential); Benchmark (surveying); Arabic; Computer science; Natural language processing; Linguistics; Artificial intelligence; Contrastive analysis; Psychology; Philosophy; Geology","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":[],"consensus_categories":[],"category_scores_codex":[0.000269889,0.00005241267,0.0001063892,0.00008787281,0.0004140954,0.00003187193,0.0004812023,0.00001319029,0.0000496941],"category_scores_gemma":[0.00006599645,0.00004972053,0.00003456822,0.0002727784,0.00001992359,0.0001334486,0.0003111498,0.0001041862,9.064546e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003609264,"about_ca_system_score_gemma":0.00002593371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001292273,"about_ca_topic_score_gemma":0.000004715724,"domain_scores_codex":[0.9992991,0.00005153125,0.0001498932,0.0001871571,0.0001836441,0.000128649],"domain_scores_gemma":[0.9995828,0.0001245214,0.0001171217,0.0001161107,0.00004901222,0.00001039473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002894115,0.0005722632,0.00738199,0.000007680153,0.00006065408,0.000001368235,0.01528652,0.0005852985,0.001970188,0.8856935,0.001947755,0.08646388],"study_design_scores_gemma":[0.01219797,0.01405795,0.09288262,0.00001159388,0.0001000082,0.00001033756,0.4213762,0.2497339,0.01156528,0.1541846,0.04239004,0.001489436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3586984,0.00002465102,0.6320052,0.001313245,0.0001864594,0.0007779468,0.00000148758,0.0006167736,0.006375821],"genre_scores_gemma":[0.9964276,2.842565e-7,0.002848474,0.00002670219,0.000008268098,0.0001897467,0.0000012262,0.000002807559,0.0004949127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7315089,"threshold_uncertainty_score":0.3184929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02750089901426163,"score_gpt":0.2749420696812646,"score_spread":0.247441170667003,"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."}}