{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004867842,0.0004042676,0.0003546857,0.00301832,0.000128254,0.0005738557,0.001175474,0.0003145212,0.0004218933],"category_scores_gemma":[0.0006004901,0.0004067698,0.00005075885,0.004253625,0.001704745,0.0009624194,0.0002529191,0.0005916052,0.007202802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054379,"about_ca_system_score_gemma":0.0008396342,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.006706127,"about_ca_topic_score_gemma":0.03353793,"domain_scores_codex":[0.99561,0.000189691,0.0006797427,0.001679483,0.001269233,0.0005718407],"domain_scores_gemma":[0.9977775,0.00003850164,0.0003986103,0.001353686,0.000152711,0.0002790445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002435042,0.0006030501,0.004906154,0.001732828,0.00004891125,0.00007398982,0.04188954,0.0004271813,0.8348387,0.01674966,0.05924617,0.03945947],"study_design_scores_gemma":[0.003845503,0.000718949,0.03002089,0.01012508,0.00060005,0.000094157,0.03898978,0.5556849,0.07085162,0.1945757,0.08433408,0.01015926],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7708908,0.009221495,0.002186161,0.002457183,0.008825077,0.006618758,0.0007310756,0.009740814,0.1893287],"genre_scores_gemma":[0.8806404,0.00003387647,0.01110664,0.0002166139,0.0009529899,0.0001316016,0.0007929069,0.001438977,0.1046859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7639871,"threshold_uncertainty_score":0.9999083,"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."}}