{"id":"W4407986476","doi":"10.1007/s10664-025-10618-0","title":"Evaluating interactive documentation for programmers","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Documentation; Computer science; World Wide Web; Software engineering; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01016158,0.0009799625,0.0008474208,0.002291322,0.00110433,0.00374444,0.001555256,0.001967097,0.004311485],"category_scores_gemma":[0.1613455,0.0004794266,0.000449154,0.00167564,0.0006947626,0.002979717,0.00203446,0.001240713,0.0009837829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001647259,"about_ca_system_score_gemma":0.002482394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004453322,"about_ca_topic_score_gemma":0.006103723,"domain_scores_codex":[0.9857779,0.007269369,0.001023756,0.0008128207,0.004664524,0.0004516212],"domain_scores_gemma":[0.7851467,0.1568357,0.01387057,0.01410782,0.02555297,0.004486238],"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":[0.008655415,0.007034823,0.1252217,0.001428661,0.0004671304,0.0007031818,0.00846014,0.03729184,0.01882802,0.003241095,0.006501003,0.7821669],"study_design_scores_gemma":[0.003478602,0.03633457,0.2538049,0.001598205,0.001974039,0.001699185,0.01309363,0.5502153,0.09596464,0.01464875,0.02672093,0.0004673089],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755727,0.0005164751,0.01457188,0.0002107512,0.00004574047,0.0001878143,0.0001602158,0.00159122,0.007143366],"genre_scores_gemma":[0.9725614,0.0001904589,0.02396233,0.00006184611,0.00002913888,0.0001054466,0.0005075435,0.0002568816,0.002325118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01016158,"threshold_uncertainty_score":0.0537402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04750618481790624,"score_gpt":0.4132381797684386,"score_spread":0.3657319949505324,"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."}}