{"id":"W4411540031","doi":"10.1016/j.datak.2025.102482","title":"Domain knowledge in artificial intelligence: Using conceptual modeling to increase machine learning accuracy and explainability","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Domain (mathematical analysis); Machine learning; Domain knowledge; Artificial Intelligence System; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001681191,0.0002563636,0.0002911777,0.0005122308,0.000196126,0.0002441871,0.001315227,0.00009464168,0.000006479631],"category_scores_gemma":[0.001783199,0.0002797999,0.00002590677,0.001187946,0.0000396167,0.000902659,0.002115458,0.0005805095,0.00002686219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001638239,"about_ca_system_score_gemma":0.0001644608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003183823,"about_ca_topic_score_gemma":0.000246959,"domain_scores_codex":[0.9978576,0.000208543,0.0005190331,0.0008911419,0.0001217794,0.0004018477],"domain_scores_gemma":[0.9980868,0.0005160269,0.00005515624,0.001097845,0.00008466942,0.0001595113],"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":[0.00005118783,0.0003334692,0.002764521,0.0003543318,0.00003753275,0.00001692566,0.008983845,0.1078154,0.005358594,0.2726089,0.00008330066,0.6015919],"study_design_scores_gemma":[0.000110385,0.00001911276,0.0002702101,0.0001534929,0.000007396895,0.000004737663,0.0004225113,0.991344,0.0001319211,0.0005830631,0.006690996,0.0002621753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1475427,0.001190301,0.8501359,0.0001786241,0.0002887541,0.000216162,0.00002483418,0.0001997243,0.0002229555],"genre_scores_gemma":[0.9018036,0.00002453436,0.09783458,0.00001914051,0.00009645215,0.00002181319,0.0001566157,0.00001730776,0.00002597387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8835285,"threshold_uncertainty_score":0.9999654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06691927417424057,"score_gpt":0.3392689324753541,"score_spread":0.2723496583011135,"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."}}