{"id":"W2165617065","doi":"10.1109/wpc.2003.1199202","title":"Observing and measuring cognitive support: steps toward systematic tool evaluation and engineering","year":2004,"lang":"en","type":"article","venue":"","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Simon Fraser University","keywords":"Computer science; Cognition; Coding (social sciences); Key (lock); Software; Field (mathematics); Comprehension; Software engineering; Human–computer interaction; Data science; Computer security; Psychology; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001027309,0.0001145011,0.000151522,0.00007950485,0.00004856519,0.0002421072,0.0001442014,0.00004172191,0.000004478387],"category_scores_gemma":[0.0006653344,0.0001035182,0.00001706833,0.0001309012,0.000007166201,0.0008332276,0.0001468473,0.00008646063,0.00000304417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004237371,"about_ca_system_score_gemma":0.00003171956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000227025,"about_ca_topic_score_gemma":0.000001621067,"domain_scores_codex":[0.9991575,0.00003054226,0.0001811136,0.0002274158,0.0002568814,0.0001464834],"domain_scores_gemma":[0.9993361,0.0002992642,0.00005690637,0.0001601984,0.00009386161,0.00005373523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000808558,0.000509258,0.01408411,0.1377958,0.001646324,0.0005043454,0.07553458,0.04474987,0.01712192,0.4339936,0.0001819096,0.2737975],"study_design_scores_gemma":[0.003013049,0.0006071223,0.0376908,0.01394065,0.0004475798,0.0009989499,0.0008035339,0.9140007,0.01746598,0.009023525,0.0001007539,0.001907294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1089764,0.000560917,0.8891698,0.000137267,0.00010072,0.0004292858,4.004617e-7,0.0005060285,0.0001191817],"genre_scores_gemma":[0.8890226,0.00003234424,0.1108141,0.00004548135,0.00001609252,0.00005371511,5.893733e-7,0.000007880647,0.000007155276],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8692509,"threshold_uncertainty_score":0.4221351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04863015337768083,"score_gpt":0.2670587353479642,"score_spread":0.2184285819702834,"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."}}