{"id":"W4384026586","doi":"10.1109/msr59073.2023.00023","title":"Evaluating Software Documentation Quality","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Documentation; Readability; Computer science; World Wide Web; Software documentation; JavaScript; Python (programming language); Software; Quality (philosophy); Java; Software engineering; Software development; Software development process; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00129784,0.0000521205,0.00005602319,0.0001147576,0.00006682472,0.0001479777,0.0004307231,0.00002123781,0.00007784819],"category_scores_gemma":[0.00209812,0.00004881614,0.00002477783,0.0008665419,0.000008426756,0.0004043817,0.000242166,0.00006789067,0.001210369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004891264,"about_ca_system_score_gemma":0.00004715358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005280242,"about_ca_topic_score_gemma":0.000002009992,"domain_scores_codex":[0.9988666,0.00006208071,0.0001276927,0.0002195896,0.0005059485,0.0002180841],"domain_scores_gemma":[0.9983725,0.001126765,0.00001794067,0.0003596416,0.00007081178,0.00005234278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004789561,0.00003664395,0.09734772,0.0001151507,0.00003412705,0.00002520623,0.002011401,0.015868,0.007780237,0.05178032,0.01466807,0.8103284],"study_design_scores_gemma":[0.0005515133,0.0001089483,0.7619926,0.00002034138,0.000001891563,0.000004588893,0.00005735718,0.2107812,0.006760033,0.01876113,0.0006151361,0.0003453087],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.203275,0.000008848589,0.7934739,0.000411821,0.00022447,0.00009222002,3.858765e-7,0.00226457,0.0002487512],"genre_scores_gemma":[0.6408581,0.000004051035,0.3553671,0.0001253043,0.00005734115,0.00005217807,0.000008046519,0.00001174727,0.003516093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.809983,"threshold_uncertainty_score":0.9995673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1352538161411699,"score_gpt":0.456957610908366,"score_spread":0.3217037947671961,"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."}}