{"id":"W4401666276","doi":"10.1007/s10618-024-01054-7","title":"Bayesian network Motifs for reasoning over heterogeneous unlinked datasets","year":2024,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Probabilistic logic; Bayesian network; Python (programming language); Data mining; Aggregate (composite); Real world data; Bayesian probability; Machine learning; Set (abstract data type); Artificial intelligence; Data science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004624117,0.0002314046,0.0003383857,0.0001706186,0.0003175814,0.002682449,0.00148112,0.00008105216,0.00006901364],"category_scores_gemma":[0.001592132,0.0001803917,0.00007776871,0.0004986452,0.0001191103,0.002316508,0.002194312,0.000108688,0.00008928861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002245979,"about_ca_system_score_gemma":0.0001074058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003748714,"about_ca_topic_score_gemma":0.0004990714,"domain_scores_codex":[0.9970461,0.0001860787,0.0005886095,0.001307238,0.0004211558,0.0004508742],"domain_scores_gemma":[0.9957396,0.001982805,0.0001001416,0.001998252,0.00003766196,0.0001415711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004114622,0.00005423227,0.0003234607,0.0001055172,0.0001060185,0.00003659696,0.0006606451,0.00007571885,0.000007249033,0.005679967,0.763801,0.2291085],"study_design_scores_gemma":[0.0002618789,0.00005913406,0.0002734814,0.000268953,0.00008943635,0.00001332386,0.0007255858,0.169614,0.000009147724,0.003017233,0.8253931,0.0002747749],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07173932,0.03800225,0.7337181,0.00128708,0.01056449,0.001589811,0.1344846,0.0005574279,0.008056971],"genre_scores_gemma":[0.8948025,0.000577729,0.02130219,0.0009935668,0.003098583,0.00009195967,0.06366882,0.0001142447,0.0153504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8230632,"threshold_uncertainty_score":0.9983529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1674946705782729,"score_gpt":0.4358667777938899,"score_spread":0.2683721072156171,"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."}}