{"id":"W4406803664","doi":"10.3390/jimaging11020033","title":"Investigating the Potential of Latent Space for the Classification of Paint Defects","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"HORIZON EUROPE Marie Sklodowska-Curie Actions; European Commission; Canadian Institute of Steel Construction","keywords":"Interpretability; Computer science; Workload; Space (punctuation); Dual (grammatical number); Machine learning; Artificial intelligence; Mechanism (biology); Data science; Risk analysis (engineering); Human–computer interaction","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105431,0.00005215223,0.0001290494,0.00008597385,0.00006701422,0.00002256177,0.00009661623,0.00002583966,0.000001437489],"category_scores_gemma":[0.0002617821,0.00002907658,0.0001262402,0.0001610909,0.00003005954,0.00006488258,0.00001120113,0.0001513979,1.781913e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003632652,"about_ca_system_score_gemma":0.00003721401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001548346,"about_ca_topic_score_gemma":0.000001367876,"domain_scores_codex":[0.9993075,0.00004583319,0.0004049673,0.00003440716,0.0001347465,0.00007251301],"domain_scores_gemma":[0.9991469,0.0002573398,0.0002923098,0.00009609762,0.0001930411,0.00001429714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003272928,0.00001378664,0.003623065,0.0002061878,0.0001615441,8.477836e-7,0.0005067644,0.08703954,0.8486183,0.001616421,0.0037092,0.05447167],"study_design_scores_gemma":[0.001393888,0.00009427353,0.05251768,0.001084245,0.0002707795,0.00005274054,0.003192492,0.7199924,0.2157262,0.001532522,0.004014704,0.0001280165],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6937939,0.001129056,0.3020118,0.0009515216,0.00158067,0.0002505644,0.000001878856,0.00001312006,0.0002675687],"genre_scores_gemma":[0.9994919,0.00001504012,0.0002881148,0.00001807894,0.0001630844,0.000002594607,1.242174e-7,0.000006216251,0.0000149048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6329529,"threshold_uncertainty_score":0.1185708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01893554143466337,"score_gpt":0.2533821251765314,"score_spread":0.2344465837418681,"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."}}