{"id":"W2770824794","doi":"10.1016/j.heares.2017.11.010","title":"A framework for testing and comparing binaural models","year":2017,"lang":"en","type":"review","venue":"Hearing Research","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Engineering and Physical Sciences Research Council; Canada Research Chairs","keywords":"Computer science; Binaural recording; Computational model; Sound localization; Experimental data; Task (project management); Cognitive science; Artificial intelligence; Speech recognition; Psychology; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.002799546,0.0002634637,0.001019624,0.0004321808,0.001660864,0.000768557,0.000580635,0.0003541525,0.000002262742],"category_scores_gemma":[0.02327414,0.0002150379,0.0001766451,0.0003607672,0.0004311868,0.0002289717,0.0006166189,0.001529219,0.00002998414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001524396,"about_ca_system_score_gemma":0.000350969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001901438,"about_ca_topic_score_gemma":0.000001551648,"domain_scores_codex":[0.9967548,0.0004468618,0.0004454323,0.000912751,0.00057142,0.0008687272],"domain_scores_gemma":[0.9879843,0.0107416,0.0001526974,0.0007491217,0.0001637645,0.0002085461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005996138,0.00002893094,0.00004427939,0.02045672,0.000006254459,0.000008282223,0.000154297,0.00001378025,0.00004975523,0.01429567,0.00002996308,0.9649061],"study_design_scores_gemma":[0.0005360087,0.0005927127,0.0003747179,0.1183693,0.0001140215,0.0001809258,0.00005793663,0.05133851,0.00002852825,0.1775842,0.6495666,0.001256483],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001580023,0.9927633,0.0008200136,0.00008252488,0.0002612392,0.002341895,0.00001080641,0.0001148877,0.002025301],"genre_scores_gemma":[0.006560948,0.9808465,0.01097985,0.00000815046,0.0003543948,0.0005455386,0.000002214416,0.00009921066,0.0006031421],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9636496,"threshold_uncertainty_score":0.9996389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8542053808368846,"score_gpt":0.5936544484729157,"score_spread":0.2605509323639689,"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."}}