{"id":"W6929283563","doi":"10.48448/1pe4-ga93","title":"Fumbling in Babel: An Investigation into ChatGPT’s Language Identification Ability","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variety (cybernetics); Language identification; Identification (biology); Benchmark (surveying); Language understanding; Constructed language; Language model","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005221611,0.001598271,0.001063791,0.002186702,0.001275483,0.002674445,0.002358269,0.00150603,0.006759544],"category_scores_gemma":[0.02282104,0.0008244099,0.001050558,0.001898883,0.001645935,0.005063745,0.004611649,0.002733244,0.004376019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001126321,"about_ca_system_score_gemma":0.001378698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01297322,"about_ca_topic_score_gemma":0.01606707,"domain_scores_codex":[0.9956931,0.001775506,0.0002324138,0.001131421,0.0007495642,0.000417923],"domain_scores_gemma":[0.9815083,0.01337133,0.000384055,0.002374561,0.001693912,0.0006678744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0053764,0.00110317,0.08830366,0.004320706,0.00116981,0.003455086,0.008404941,0.159781,0.02587684,0.0215492,0.2140196,0.4666396],"study_design_scores_gemma":[0.0003600913,0.001418097,0.02269102,0.0004966584,0.0003194763,0.001587428,0.004021661,0.8215731,0.04210761,0.0193255,0.08576528,0.0003341591],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7397115,0.003303638,0.07869876,0.001476938,0.001182166,0.0002746547,0.01520563,0.1283728,0.03177386],"genre_scores_gemma":[0.8466406,0.0005914086,0.07806001,0.0009787227,0.0001523499,0.0002748934,0.05143837,0.01132013,0.01054355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01297322,"threshold_uncertainty_score":0.02761483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02861803456834339,"score_gpt":0.3477648522130816,"score_spread":0.3191468176447382,"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."}}