{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01177757,0.0004755002,0.0004723067,0.0009752677,0.0002628985,0.0008780805,0.0004916464,0.000693854,0.001118832],"category_scores_gemma":[0.0436779,0.0003283932,0.0003763877,0.0003439457,0.0009381213,0.0007453567,0.001628252,0.0005571425,0.0008486285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320864,"about_ca_system_score_gemma":0.0001461158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005837777,"about_ca_topic_score_gemma":0.0006509378,"domain_scores_codex":[0.9902202,0.003822502,0.0008907939,0.001870626,0.002918152,0.0002777988],"domain_scores_gemma":[0.9514214,0.03229885,0.004016659,0.006516884,0.00515026,0.0005960042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005353784,0.0004108206,0.5527107,0.0004910392,0.001091078,0.0003812085,0.01493982,0.001792726,0.2884034,0.0004692465,0.0005011819,0.1334549],"study_design_scores_gemma":[0.00002863881,0.001931835,0.9699684,0.00004217899,0.0001391176,0.000639367,0.001283646,0.002064683,0.02265367,0.0004061363,0.0007706849,0.00007167296],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892886,0.0003485561,0.007937455,0.00002259864,0.00004289614,0.00003800492,0.0000843423,0.00004619708,0.002191427],"genre_scores_gemma":[0.9974484,0.00006617429,0.001833836,0.00001676613,0.00002073031,0.000027865,0.0001152039,0.00003767065,0.0004333478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01177757,"threshold_uncertainty_score":0.06228644,"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."}}