{"id":"W4317941305","doi":"10.1103/physrevc.107.014321","title":"Interpretable boosted-decision-tree analysis for the Majorana Demonstrator","year":2023,"lang":"en","type":"article","venue":"Physical review. C","topic":"Neutrino Physics Research","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Lawrence Berkeley National Laboratory; Oak Ridge National Laboratory; Nuclear Physics; Los Alamos National Laboratory; Natural Sciences and Engineering Research Council of Canada; Laboratory Directed Research and Development; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Interpretability; MAJORANA; Decision tree; Machine learning; Artificial intelligence; Physics; Detector; Alternating decision tree; Double beta decay; Tree (set theory); Germanium; Particle physics; Computer science; Data mining; Decision tree learning; Neutrino; Incremental decision tree; Optics; Optoelectronics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000436231,0.0002224134,0.0006141994,0.0001042684,0.0002276912,0.00009729507,0.0006698425,0.00001583295,0.0002443826],"category_scores_gemma":[0.00002563996,0.0001440599,0.0009674252,0.002632932,0.00008460588,0.0001465305,0.0002302359,0.0002569466,0.000811399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002273634,"about_ca_system_score_gemma":0.00006812937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005100936,"about_ca_topic_score_gemma":0.000007264148,"domain_scores_codex":[0.9982159,0.00007207523,0.00032716,0.0004213021,0.0004556059,0.0005080145],"domain_scores_gemma":[0.9970149,0.001782505,0.0001107991,0.0007871017,0.0001573978,0.0001473256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008181642,0.0006041693,0.01812034,0.0004790222,0.004161729,0.000004315814,0.0001595278,0.0008030907,0.00588187,0.2143874,0.07852453,0.6767922],"study_design_scores_gemma":[0.003132378,0.0004637792,0.03349426,0.002278127,0.0110261,0.000001146324,0.0004979419,0.3056491,0.04027965,0.3443862,0.256096,0.002695241],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.36547,0.01481056,0.4123371,0.01409902,0.001169362,0.01434773,0.002094571,0.0009697021,0.174702],"genre_scores_gemma":[0.9977599,0.0003589098,0.00006589226,0.0001747263,0.000486254,0.0005532327,0.00007469404,0.00003189448,0.0004944586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.674097,"threshold_uncertainty_score":0.9999666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03138385404952071,"score_gpt":0.3996604377500428,"score_spread":0.3682765837005221,"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."}}