{"id":"W4409405484","doi":"10.1007/s10664-025-10651-z","title":"Predicting the understandability of computational notebooks through code metrics analysis","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Computer science; Programming language; Code (set theory)","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":[],"consensus_categories":[],"category_scores_codex":[0.000753136,0.0001894435,0.000340315,0.000434201,0.0001357627,0.0000989037,0.001069035,0.0001013783,0.000008595207],"category_scores_gemma":[0.006151878,0.0001533485,0.0002319919,0.005106668,0.00007741563,0.0002041871,0.0004668231,0.0004072217,0.000002755656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002465734,"about_ca_system_score_gemma":0.0001607061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004545998,"about_ca_topic_score_gemma":0.000004874494,"domain_scores_codex":[0.998014,0.00006291727,0.0004427471,0.0004261198,0.0006791393,0.0003750873],"domain_scores_gemma":[0.9909049,0.008033009,0.00006672711,0.0007002655,0.0002208481,0.00007422304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002569386,0.00002750023,0.3893409,0.00006206812,0.0003026762,0.000002409053,0.0003969528,0.6075402,0.00000549165,0.001578678,0.0001686567,0.0005718502],"study_design_scores_gemma":[0.0002147764,0.00002924071,0.3927418,0.00003479729,0.00009423342,0.000001935924,0.00002102161,0.6027882,0.0003698849,0.002497398,0.00102419,0.0001825963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09295937,0.0002573724,0.9052759,0.0004913938,0.0002339862,0.0001618571,0.00001195794,0.0005632672,0.00004489977],"genre_scores_gemma":[0.8785625,0.000003060404,0.1212382,0.0000998882,0.00002578085,0.00001788729,0.000004812607,0.00001132703,0.00003661571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.785603,"threshold_uncertainty_score":0.7364817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03729922534070134,"score_gpt":0.3189262083606235,"score_spread":0.2816269830199222,"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."}}