{"id":"W4389192166","doi":"10.22215/etd/2023-15659","title":"Using Automated Facial Recognition to Select Fillers for Eyewitness Identification Lineups","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Suspect; Eyewitness identification; Similarity (geometry); Identification (biology); Psychology; Recall; Artificial intelligence; Pattern recognition (psychology); Computer science; Cognitive psychology; Data mining; Criminology","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":[0.006240753,0.0009946361,0.0009176172,0.001795867,0.0006839813,0.001209368,0.0008941261,0.0007806099,0.01693433],"category_scores_gemma":[0.03127325,0.0004022207,0.0005967111,0.0003809672,0.0004062823,0.001740404,0.001260845,0.0007106382,0.007036087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004032514,"about_ca_system_score_gemma":0.0004347784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005623073,"about_ca_topic_score_gemma":0.001466248,"domain_scores_codex":[0.9972039,0.0009582331,0.0003026256,0.0006809473,0.0006946397,0.0001596775],"domain_scores_gemma":[0.9845068,0.008218098,0.002028976,0.001935088,0.002822612,0.0004885363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005287507,0.002635282,0.05905263,0.0008439088,0.00008391945,0.0007793289,0.007116822,0.002142042,0.1487665,0.002467277,0.01720692,0.7536179],"study_design_scores_gemma":[0.001416623,0.02025545,0.5009004,0.001018525,0.000385715,0.004623337,0.01590999,0.1119205,0.2534918,0.01545445,0.07377191,0.0008513157],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8839663,0.00021699,0.08768103,0.0003491279,0.0002290834,0.008854491,0.001672479,0.002800665,0.01422976],"genre_scores_gemma":[0.7591472,0.0002797185,0.2210917,0.0004118472,0.000130967,0.008230442,0.001753039,0.0004130334,0.008541925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01693433,"threshold_uncertainty_score":0.056651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1347811026641128,"score_gpt":0.4506581312615901,"score_spread":0.3158770285974772,"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."}}