{"id":"W4400267760","doi":"10.1145/3649217.3653545","title":"Are a Static Analysis Tool Study's Findings Static? A Replication","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Static analysis; Computer science; Replication (statistics); Programming language; Mathematics; Statistics","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":[0.001043336,0.0001012524,0.0001523616,0.0003439817,0.0001315452,0.0009275309,0.0004110671,0.0000218514,0.00003203954],"category_scores_gemma":[0.000213383,0.00008280551,0.00009035134,0.00175955,0.0000111755,0.0003213566,0.0001057263,0.0001949079,0.0001074939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004973854,"about_ca_system_score_gemma":0.00003013931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637353,"about_ca_topic_score_gemma":0.00003876996,"domain_scores_codex":[0.9985882,0.0001314752,0.0002151415,0.0005905657,0.0002762691,0.0001983318],"domain_scores_gemma":[0.998868,0.0001982253,0.00005908942,0.0007917015,0.0000351998,0.00004772864],"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":[0.000003883722,0.0003232733,0.07991096,0.00008422283,0.001021528,0.0001257942,0.03789824,0.002428972,0.00003228656,0.01761349,0.002859863,0.8576975],"study_design_scores_gemma":[0.0002353599,0.0002693541,0.1609798,0.00006088776,0.0004593303,0.000009668835,0.00329885,0.7722969,0.00003200185,0.0007308721,0.06118513,0.0004418528],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2997618,0.00003630967,0.6978127,0.00128602,0.00006683884,0.0001407194,5.823593e-7,0.000803759,0.00009130886],"genre_scores_gemma":[0.9274949,7.480763e-7,0.07023844,0.0001637261,0.00001560963,0.00003991221,0.00000281973,0.000007474637,0.002036304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8572556,"threshold_uncertainty_score":0.8944202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02653728832208449,"score_gpt":0.3193673178622187,"score_spread":0.2928300295401343,"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."}}