{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1392094,0.00292916,0.002638352,0.01327123,0.003962754,0.01125835,0.004900678,0.003583311,0.001161083],"category_scores_gemma":[0.2757426,0.001587759,0.001062269,0.005693218,0.004715173,0.0155008,0.006053946,0.0044159,0.0006220452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003816992,"about_ca_system_score_gemma":0.01883233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00812836,"about_ca_topic_score_gemma":0.01329009,"domain_scores_codex":[0.8571438,0.09628212,0.01487645,0.00398395,0.026032,0.001681746],"domain_scores_gemma":[0.6451636,0.223039,0.0233664,0.03513368,0.06892772,0.004369464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004213733,0.003165106,0.08039945,0.004225179,0.0002258085,0.000322109,0.03716162,0.00287427,0.02292946,0.01414236,0.003148767,0.8309845],"study_design_scores_gemma":[0.001491026,0.01420065,0.2334281,0.01233831,0.001096471,0.001826455,0.2030624,0.0988641,0.138565,0.2167983,0.07633388,0.001995167],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1504718,0.001893464,0.8186166,0.003850425,0.0001208377,0.01611691,0.0003722194,0.001742078,0.006815565],"genre_scores_gemma":[0.1249382,0.0004144041,0.8687759,0.0002247992,0.00002048379,0.005063106,0.0001278263,0.00005956897,0.0003757396],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1392094,"threshold_uncertainty_score":0.7362183,"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."}}