{"id":"W4400142487","doi":"10.1145/3643834.3660692","title":"Do LLMs Meet the Needs of Software Tutorial Writers? Opportunities and Design Implications","year":2024,"lang":"en","type":"article","venue":"Designing Interactive Systems Conference","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software; Software engineering; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001120301,0.0002448645,0.0003163471,0.0002920617,0.0002457886,0.001318635,0.0007044931,0.00008295084,0.000008177415],"category_scores_gemma":[0.0002059273,0.0001765867,0.00008301705,0.0003368005,0.0001161535,0.0008534914,0.0001905302,0.000278628,0.00001436515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008042117,"about_ca_system_score_gemma":0.0002471613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001846944,"about_ca_topic_score_gemma":0.000001038296,"domain_scores_codex":[0.9980028,0.0005909652,0.000481125,0.0003664374,0.000274884,0.0002837335],"domain_scores_gemma":[0.9968731,0.001875157,0.0002402117,0.0004656595,0.0004625723,0.00008325357],"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":[0.00001481015,0.00001344544,0.0001470693,0.0001352963,0.0001374325,0.00001395274,0.01827212,0.0003549772,0.006999763,0.9663496,0.0009003293,0.006661217],"study_design_scores_gemma":[0.001589765,0.003819976,0.001911663,0.0285146,0.0004835045,0.002321124,0.1414083,0.3892674,0.05175171,0.02695339,0.3472129,0.004765735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001670763,0.001140169,0.991595,0.0003336413,0.003158977,0.0004878129,0.00001102626,0.0002263843,0.001376278],"genre_scores_gemma":[0.9924627,0.00003317676,0.004749738,0.00002233125,0.0002899768,0.0001311235,0.000001605424,0.00002067102,0.002288654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.990792,"threshold_uncertainty_score":0.9997181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179212593245751,"score_gpt":0.2957797743000063,"score_spread":0.1778585149754312,"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."}}