{"id":"W2890502052","doi":"","title":"[Journal First] Measuring Program Comprehension: A Large-Scale Field Study with Professionals","year":2018,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Program comprehension; Comprehension; Computer science; Field (mathematics); Software engineering; World Wide Web; Software; Multimedia; Human–computer interaction; Programming language; Software system","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":[],"consensus_categories":[],"category_scores_codex":[0.000476912,0.0002820379,0.0002326117,0.0003676409,0.000245621,0.0004863569,0.001530246,0.00008275313,0.0001716933],"category_scores_gemma":[0.0008367948,0.0002354845,0.0000660541,0.000398471,0.00002829435,0.000533545,0.0004089814,0.0006573997,0.00008491483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001394114,"about_ca_system_score_gemma":0.0001405991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006749629,"about_ca_topic_score_gemma":0.0000188293,"domain_scores_codex":[0.9973381,0.00003917421,0.0003231116,0.0005085692,0.00127822,0.0005128749],"domain_scores_gemma":[0.9977539,0.0005179796,0.00009071991,0.0005119613,0.0009058008,0.0002196914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001100403,0.01023228,0.7874532,0.0003634208,0.002086587,0.00205743,0.02866046,0.02619492,0.0007316193,0.02139948,0.009234623,0.1104855],"study_design_scores_gemma":[0.005570414,0.01064422,0.2717728,0.003099434,0.0000360946,0.0007015827,0.00117951,0.6793474,0.004196507,0.0002786701,0.02095193,0.002221483],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.358967,0.00002034805,0.637003,0.000641476,0.001630844,0.0005112419,0.00000309004,0.001049519,0.0001734704],"genre_scores_gemma":[0.9034349,0.000003018385,0.09572797,0.00008886125,0.0004232777,0.0001315014,0.000002382066,0.00003166607,0.0001564751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6531525,"threshold_uncertainty_score":0.960278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04064767116405217,"score_gpt":0.3180627877946147,"score_spread":0.2774151166305626,"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."}}