{"id":"W4413276718","doi":"10.1139/cjm-2025-0038","title":"A comprehensive guide to selecting the right modeling strategy for explanatory and predictive data analysis","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Microbiology","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Explanatory model; Computer science; Econometrics; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0122451,0.003653341,0.001975224,0.004312124,0.001245458,0.003815203,0.004568479,0.003942496,0.03108778],"category_scores_gemma":[0.04164029,0.002503017,0.002238255,0.003337499,0.00149589,0.002871052,0.002565463,0.007272913,0.0230085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001937989,"about_ca_system_score_gemma":0.008471786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007853916,"about_ca_topic_score_gemma":0.0182485,"domain_scores_codex":[0.9952685,0.002599349,0.0006332555,0.0003328828,0.001049682,0.0001164077],"domain_scores_gemma":[0.9702597,0.02231164,0.0009896609,0.001354136,0.004628909,0.0004560411],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001085684,0.0003429464,0.001269303,0.003016387,0.0001288455,0.0007591708,0.0005441452,0.02858609,0.002851383,0.09924345,0.5602948,0.3028549],"study_design_scores_gemma":[0.0001019753,0.0001964985,0.0009742249,0.002356429,0.00005234303,0.000793867,0.0002589551,0.0572283,0.001799524,0.1286629,0.8074072,0.0001678319],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007472393,0.003104111,0.9621762,0.006485392,0.0006252165,0.001869666,0.008791567,0.006909915,0.009290808],"genre_scores_gemma":[0.001881326,0.002430397,0.9818771,0.001628494,0.0002186698,0.00197746,0.003049794,0.0006700259,0.006266627],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9877549,"threshold_uncertainty_score":0.103999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0283530565783798,"score_gpt":0.3035750091330248,"score_spread":0.275221952554645,"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."}}