{"id":"W3028186432","doi":"10.1002/cem.3247","title":"Two‐stage approach for the inference of the source of high‐dimensional and complex chemical data in forensic science","year":2020,"lang":"en","type":"article","venue":"Journal of Chemometrics","topic":"Forensic Fingerprint Detection Methods","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"National Institute of Justice","keywords":"Inference; Computer science; Bayes' theorem; Leverage (statistics); Statistical inference; Forensic science; Kernel (algebra); Data mining; Machine learning; Artificial intelligence; Bayesian probability; Mathematics; Statistics; Archaeology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004531083,0.00007446628,0.0002751627,0.0002462748,0.0001463966,0.00003191228,0.001180677,0.00005025615,0.000007841385],"category_scores_gemma":[0.01737425,0.00004559446,0.0000648788,0.003718492,0.001666699,0.00020383,0.0004476089,0.0002863414,6.039564e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005676602,"about_ca_system_score_gemma":0.0003874715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001742668,"about_ca_topic_score_gemma":0.00001076089,"domain_scores_codex":[0.9981105,0.00009634823,0.000470675,0.0001635011,0.0009808906,0.0001780563],"domain_scores_gemma":[0.9971651,0.001366015,0.0006309813,0.0002675028,0.0004773203,0.00009302113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001109595,0.0007125054,0.08347182,0.0007626513,0.0002104066,0.000004949295,0.03090286,0.01734317,0.3356531,0.0506321,0.003209732,0.4759871],"study_design_scores_gemma":[0.008560809,0.0008582292,0.1270083,0.0002850635,0.0003917873,0.00007743962,0.01640207,0.4730054,0.3362394,0.01018018,0.0260336,0.0009577394],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8994102,0.0002624447,0.09494269,0.00435314,0.0003189777,0.0003212101,0.00001916282,0.000005775009,0.0003663841],"genre_scores_gemma":[0.9194486,0.00001964319,0.08023408,0.0001814416,0.00009684232,6.826693e-7,5.143863e-7,0.000004971789,0.00001328303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4750294,"threshold_uncertainty_score":0.9909028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1542855914165787,"score_gpt":0.3859632244995684,"score_spread":0.2316776330829897,"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."}}