{"id":"W4391765300","doi":"10.16995/labphon.9379","title":"Variability and reliability in the AXB assessment of phonetic imitation","year":2024,"lang":"en","type":"article","venue":"Laboratory Phonology Journal of the Association for Laboratory Phonology","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Imitation; Reliability (semiconductor); Computer science; Speech recognition; Psychology; Neuroscience; Physics","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":[0.01039724,0.0002557414,0.0006589142,0.0003947239,0.0001741444,0.00005497072,0.0008641684,0.0008853553,0.0001082102],"category_scores_gemma":[0.001958707,0.0001749686,0.0001891664,0.001461711,0.0005583261,0.0002009442,0.0001230256,0.00184016,0.00001217263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000536593,"about_ca_system_score_gemma":0.001114683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003458333,"about_ca_topic_score_gemma":0.00006845562,"domain_scores_codex":[0.993478,0.00388166,0.001257925,0.0004561734,0.0003841705,0.000542057],"domain_scores_gemma":[0.9923046,0.004689752,0.001027498,0.0007022016,0.001203297,0.00007261442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009005715,0.001702267,0.8355601,0.0004222828,0.001614092,0.00005664273,0.02897557,0.0003531411,0.0521196,0.0486854,0.02736764,0.002242647],"study_design_scores_gemma":[0.001867601,0.0006954381,0.9482769,0.00004748665,0.0002077925,0.00003624407,0.001253514,0.0002094952,0.001215245,0.02305188,0.02293276,0.0002056836],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843839,0.001834394,0.0002153502,0.007609743,0.004471991,0.0006694622,0.0003059293,0.00002411031,0.0004851669],"genre_scores_gemma":[0.9983855,0.0001818512,0.0004428499,0.0005611026,0.0001935325,0.0001032852,0.000006528227,0.0000296688,0.00009562598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1127167,"threshold_uncertainty_score":0.7994681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01415282375969802,"score_gpt":0.3437581948813157,"score_spread":0.3296053711216177,"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."}}