{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02668586,0.00210898,0.001462318,0.002228301,0.001640371,0.004467254,0.00784261,0.002691767,0.01005394],"category_scores_gemma":[0.1508243,0.00149665,0.001119119,0.001224573,0.007115214,0.01252253,0.009434592,0.005010175,0.002934703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001447178,"about_ca_system_score_gemma":0.00426681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229738,"about_ca_topic_score_gemma":0.001844765,"domain_scores_codex":[0.9739901,0.01530107,0.001407218,0.003309391,0.005061028,0.0009310524],"domain_scores_gemma":[0.8517625,0.1080505,0.006091371,0.02458314,0.007471116,0.002041333],"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":[0.001212175,0.0009527134,0.005053768,0.001095702,0.0001276287,0.0003879412,0.008303394,0.04376373,0.01625007,0.07810511,0.009738579,0.8350092],"study_design_scores_gemma":[0.0007532531,0.002239253,0.001880646,0.000980192,0.0001706871,0.0009633081,0.001805919,0.5371883,0.06978351,0.3092409,0.07450444,0.0004895851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0212482,0.0003332973,0.9638849,0.0006064978,0.0001019095,0.000449438,0.00004205074,0.01024754,0.003086026],"genre_scores_gemma":[0.1812861,0.0002956745,0.8119121,0.0002914703,0.00005576023,0.001054312,0.0001085344,0.001559765,0.003436311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02668586,"threshold_uncertainty_score":0.14113,"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."}}