{"id":"W4402905912","doi":"10.1167/jov.24.10.1259","title":"Evaluating the Alignment of Machine and Human Explanations in Visual Object Recognition through a Novel Behavioral Approach","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Object (grammar); Artificial intelligence; Cognitive neuroscience of visual object recognition; Cognitive psychology; Human–computer interaction; Psychology; Cognitive science; Computer vision","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":[0.004177471,0.0006618526,0.0003820802,0.001256847,0.0003015817,0.001307262,0.001009415,0.001049873,0.001856887],"category_scores_gemma":[0.0249126,0.0003438127,0.0006546683,0.0004461954,0.001050096,0.002175606,0.001467744,0.0009932891,0.0002174511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001112507,"about_ca_system_score_gemma":0.0006154487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003023781,"about_ca_topic_score_gemma":0.003694803,"domain_scores_codex":[0.9979401,0.0009618319,0.0001163707,0.0005042586,0.0003763809,0.0001009732],"domain_scores_gemma":[0.9857994,0.00932992,0.001843888,0.001751727,0.0008547013,0.0004204184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003623866,0.002114534,0.3209288,0.0006236561,0.001218452,0.0003565825,0.004163858,0.2107165,0.09326987,0.02090029,0.00210702,0.3399765],"study_design_scores_gemma":[0.0000597392,0.001070256,0.1297955,0.00002810474,0.0001331327,0.0001887202,0.0005978181,0.8322913,0.01818729,0.01675787,0.0008129829,0.00007726411],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8545714,0.0001520207,0.141112,0.0003661455,0.00002164952,0.0001239993,0.0003022114,0.0005731138,0.002777434],"genre_scores_gemma":[0.9702622,0.00002485208,0.02899337,0.0000534884,0.000008481775,0.00005226409,0.0002762154,0.00003765073,0.0002914557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004177471,"threshold_uncertainty_score":0.02209282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1013307266382599,"score_gpt":0.4334510801855166,"score_spread":0.3321203535472567,"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."}}