{"id":"W2012283428","doi":"10.1145/1709424.1709460","title":"Naturally occurring data as research instrument","year":2010,"lang":"en","type":"article","venue":"ACM SIGCSE Bulletin","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Taxonomy (biology); Syntax; Tracing; Programming language; Code (set theory); Replication (statistics); Extension (predicate logic); Mathematics education; Natural language processing; Psychology; Mathematics","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":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003611175,0.0001388636,0.000125835,0.000146329,0.000507289,0.0006087784,0.006953902,0.0001092984,0.0001650942],"category_scores_gemma":[0.00449385,0.0001253506,0.00003438504,0.0003084257,0.00009710118,0.0002077247,0.005423148,0.002150497,0.001823596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002317442,"about_ca_system_score_gemma":0.000105439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007001134,"about_ca_topic_score_gemma":0.00003465335,"domain_scores_codex":[0.9975491,0.0002643071,0.0002016096,0.0007332859,0.0006623555,0.0005894105],"domain_scores_gemma":[0.9954928,0.0006074999,0.00006430994,0.003571328,0.00009611464,0.0001679325],"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":[0.000007842966,0.00007936616,0.001232,0.00001274473,0.0000145263,0.00006004046,0.001570146,0.000007097337,0.0009069715,0.01738775,0.026454,0.9522675],"study_design_scores_gemma":[0.0001916223,0.00006865826,0.0008504811,0.00002737432,0.000001887784,0.00004801157,0.00009127847,0.0004978678,0.0002803911,0.0004082616,0.9973665,0.0001676411],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9205192,0.000344411,0.008358786,0.06045391,0.002759943,0.0004834041,0.000004065459,0.001345551,0.005730689],"genre_scores_gemma":[0.7922457,0.000004202663,0.206018,0.0005171904,0.0002263582,0.00001092919,0.000009365614,0.00001481359,0.0009534171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9709125,"threshold_uncertainty_score":0.9989536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1137497967383913,"score_gpt":0.3855628700363099,"score_spread":0.2718130732979185,"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."}}