{"id":"W840856345","doi":"10.1016/j.scijus.2015.06.005","title":"A demonstration of the application of the new paradigm for the evaluation of forensic evidence under conditions reflecting those of a real forensic-voice-comparison case","year":2015,"lang":"en","type":"article","venue":"Science & Justice","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Australian Government; Australasian Speech Science and Technology Association; Australian Research Council; Australian Federal Police","keywords":"Suspect; Computer science; Landline; Reliability (semiconductor); Sampling (signal processing); Telecommunications; Phone; Psychology","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":[0.003725656,0.00008979643,0.0001560468,0.00007016259,0.0003564282,0.00005062264,0.00103778,0.00003735736,4.613421e-7],"category_scores_gemma":[0.001976341,0.00005077936,0.00007360827,0.001717595,0.0007606891,0.0007614366,0.0001521909,0.00009133133,3.274332e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008851189,"about_ca_system_score_gemma":0.002014319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004431872,"about_ca_topic_score_gemma":0.0007078971,"domain_scores_codex":[0.9979182,0.0001262692,0.0004649159,0.0002667414,0.001037081,0.0001868016],"domain_scores_gemma":[0.9962223,0.000777769,0.0009779383,0.0007168513,0.001251284,0.00005384321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009126333,0.000229114,0.005006733,0.000399298,0.0000439921,4.811182e-7,0.02440191,0.1048082,0.4582793,0.1197907,0.001070016,0.2858789],"study_design_scores_gemma":[0.0003399542,0.0001052827,0.005846424,0.0002561111,0.0003477298,0.00004929593,0.003317472,0.4303346,0.5263172,0.03299968,0.000008375765,0.00007790822],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4417428,0.0002911451,0.5548315,0.001598865,0.0003335797,0.0008462381,0.000004088913,0.00001211885,0.0003396554],"genre_scores_gemma":[0.9797508,0.000004527624,0.02010815,0.00005503864,0.0000408068,0.0000282113,3.805561e-7,0.000003420137,0.000008719885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5380079,"threshold_uncertainty_score":0.3573315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2238696032448009,"score_gpt":0.4455942298542386,"score_spread":0.2217246266094377,"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."}}