{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04402148,0.0008713163,0.0009587529,0.01087415,0.0009256935,0.002962571,0.0009625619,0.001020794,0.001768476],"category_scores_gemma":[0.2054072,0.0004585736,0.001017843,0.005655726,0.0007937435,0.004009008,0.002224765,0.0009055458,0.0007027783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002067806,"about_ca_system_score_gemma":0.002327184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002290433,"about_ca_topic_score_gemma":0.003512022,"domain_scores_codex":[0.9451041,0.01637797,0.008604826,0.00243586,0.02613659,0.001340588],"domain_scores_gemma":[0.6631489,0.1637052,0.04438791,0.01180148,0.1119848,0.004971639],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008267218,0.001165837,0.3518098,0.003016233,0.0006011536,0.0002776492,0.01201401,0.005279807,0.01657878,0.002231028,0.008177631,0.5980213],"study_design_scores_gemma":[0.0002442628,0.007013394,0.8354435,0.002504899,0.0007858679,0.001128825,0.01333294,0.04767794,0.04853901,0.004205218,0.03853824,0.0005858817],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9299755,0.001778008,0.0536866,0.0006477468,0.0001373412,0.0009819143,0.001039092,0.001603648,0.01015033],"genre_scores_gemma":[0.908239,0.0008455998,0.08534432,0.0001472108,0.0000600981,0.000671525,0.002168764,0.0003285277,0.002194978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9559785,"threshold_uncertainty_score":0.2328106,"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."}}