{"id":"W4225094266","doi":"10.1145/3491102.3501895","title":"Supercharging Trial-and-Error for Learning Complex Software Applications","year":2022,"lang":"en","type":"article","venue":"CHI Conference on Human Factors in Computing Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Autodesk (Canada); University of Waterloo","funders":"","keywords":"Computer science; Software; Proof of concept; Key (lock); Software engineering; Machine learning; Data science; Programming language; Computer security","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001212734,0.0002509443,0.0004176828,0.0004628515,0.001144184,0.0003848536,0.001213113,0.00005921844,0.00001509605],"category_scores_gemma":[0.0003796888,0.0002695989,0.00007816138,0.0004476033,0.00005394521,0.0001167069,0.0006630321,0.0006921277,0.000004624828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002918519,"about_ca_system_score_gemma":0.0001031795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000992718,"about_ca_topic_score_gemma":0.000003499628,"domain_scores_codex":[0.997427,0.0002973533,0.0005001436,0.0007367251,0.0004974463,0.0005413177],"domain_scores_gemma":[0.9972569,0.001830393,0.0001514867,0.0005408132,0.00009951927,0.000120918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003927298,0.0007963231,0.2158878,0.00131912,0.0001603106,0.00002685645,0.02491563,0.2969302,0.002548676,0.4339808,0.0008174959,0.02222407],"study_design_scores_gemma":[0.01156443,0.00136968,0.02729486,0.000344247,0.00000930423,0.00002292606,0.002042149,0.948108,0.00007244794,0.001135673,0.00688566,0.001150678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5141856,0.0000693788,0.4830338,0.00005523985,0.0004657817,0.001542373,0.000009992198,0.0005674476,0.00007034546],"genre_scores_gemma":[0.9964579,0.000001532577,0.00266369,0.00001925801,0.000121036,0.0005341551,0.00003641655,0.00003335984,0.0001327019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6511778,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1725917647466699,"score_gpt":0.3652937626882987,"score_spread":0.1927019979416288,"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."}}