{"id":"W2067072439","doi":"10.1145/1370114.1370122","title":"Creating a cognitive metric of programming task difficulty","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Task (project management); Metric (unit); Selection (genetic algorithm); Software; Code (set theory); Human–computer interaction; Programming language; Cognition; Task analysis; Base (topology); Machine learning; Software engineering; Artificial intelligence; Psychology; Engineering","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":[0.000160094,0.00007129765,0.0001136592,0.0002089034,0.00006856237,0.00002502319,0.0003566275,0.00002737754,0.000008765873],"category_scores_gemma":[0.001410515,0.00005903553,0.0000420344,0.001363999,0.00004433175,0.0001712232,0.0001842603,0.00009671987,0.00001947243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272991,"about_ca_system_score_gemma":0.00004640075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006956612,"about_ca_topic_score_gemma":9.311797e-7,"domain_scores_codex":[0.999056,0.00002154389,0.0001360553,0.0002016286,0.0003547058,0.0002299958],"domain_scores_gemma":[0.9984446,0.001096548,0.00003272661,0.0001866649,0.0001704796,0.00006898184],"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":[0.00001583999,0.0007304306,0.2888538,0.0001785716,0.0001844969,0.0003100904,0.009663261,0.0005377706,0.004300133,0.006958864,0.0006980567,0.6875687],"study_design_scores_gemma":[0.00184629,0.00069733,0.84498,0.0002032203,0.00001703735,0.0004630008,0.0003899196,0.07756077,0.07232468,0.00009926429,0.0006472954,0.0007711956],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.385619,0.00007234664,0.6131791,0.00001263727,0.00002714122,0.0001140766,5.200196e-7,0.0002385549,0.0007365942],"genre_scores_gemma":[0.9001569,0.000004265311,0.09952933,0.000006223102,0.00001563796,0.00001605017,8.082847e-7,0.000005204743,0.0002655409],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6867975,"threshold_uncertainty_score":0.2407399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02659999631309141,"score_gpt":0.2775308181380765,"score_spread":0.2509308218249851,"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."}}