{"id":"W4403976907","doi":"10.1371/journal.pone.0310840","title":"Selecting optimal software code descriptors—The case of Java","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Analytical Center for the Government of the Russian Federation","keywords":"Computer science; Java; Overfitting; Software; Class (philosophy); Collinearity; Set (abstract data type); Metric (unit); Data mining; Perspective (graphical); Identification (biology); Software metric; Machine learning; Software development; Focus (optics); Similarity (geometry); Source lines of code; Artificial intelligence; Software quality; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003431518,0.001254238,0.001375403,0.004335419,0.0007147582,0.001555934,0.001224419,0.001214936,0.000506854],"category_scores_gemma":[0.01524535,0.0003099195,0.00106865,0.003120458,0.0007785343,0.001685536,0.001115117,0.0009518249,0.0004622091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104309,"about_ca_system_score_gemma":0.001815386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006844806,"about_ca_topic_score_gemma":0.009308751,"domain_scores_codex":[0.9963582,0.001037635,0.0003225895,0.00101565,0.0009982684,0.0002675675],"domain_scores_gemma":[0.9946592,0.002503337,0.0004674891,0.0007739372,0.001228107,0.0003678504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001120759,0.001133475,0.09439606,0.001450191,0.0003575776,0.001244074,0.0008786474,0.1136654,0.01974254,0.005651178,0.02496098,0.7353991],"study_design_scores_gemma":[0.0003031654,0.0007158423,0.04196596,0.0002295687,0.0002340338,0.001084042,0.001376097,0.890119,0.01951015,0.02353776,0.02083982,0.00008452927],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8888668,0.002828743,0.09921998,0.001040893,0.0001038517,0.0002208631,0.003092458,0.001842511,0.002784012],"genre_scores_gemma":[0.8064396,0.0005272938,0.1805805,0.0001536015,0.0000439537,0.0002117863,0.01036926,0.0004219598,0.001251954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006844806,"threshold_uncertainty_score":0.01814783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05683408453195925,"score_gpt":0.2655602238300151,"score_spread":0.2087261392980558,"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."}}