{"id":"W2056825598","doi":"10.1145/2538862.2538966","title":"Identifying challenging CS1 concepts in a large problem dataset","year":2014,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Code (set theory); Data science; Term (time); Information retrieval; Mathematics education; Programming language; Psychology","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":[0.001384347,0.00009423125,0.0001175985,0.0001146013,0.0001435892,0.0002439972,0.000599739,0.00003799336,0.00001534316],"category_scores_gemma":[0.00006559886,0.00008706239,0.00002441902,0.0002073579,0.00001229636,0.0004210896,0.0002914483,0.0002773346,0.0001032393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000194555,"about_ca_system_score_gemma":0.00001191014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001308914,"about_ca_topic_score_gemma":0.00008567186,"domain_scores_codex":[0.9987807,0.0001610792,0.0001704599,0.0003440439,0.0001636623,0.0003800519],"domain_scores_gemma":[0.9993935,0.00008733367,0.00005039465,0.0003979444,0.00001023974,0.00006061931],"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":[0.000001619083,0.0001160809,0.006117973,0.00006218729,0.000009487829,0.00002003146,0.009102299,0.0004999111,0.00009960291,0.273073,0.00167092,0.7092268],"study_design_scores_gemma":[0.001049129,0.00007701022,0.00678245,0.0001720425,0.000003329998,0.00002178658,0.0004387829,0.1673955,0.00007706765,0.001151306,0.8223825,0.0004491126],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00370304,0.00007882851,0.9937195,0.0005979054,0.0001284868,0.00008316063,0.000002236165,0.0003311193,0.001355678],"genre_scores_gemma":[0.869438,0.000002201112,0.1301108,0.0002154291,0.00003552022,0.000009066574,0.00002973496,0.000006581294,0.000152686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8657349,"threshold_uncertainty_score":0.3550301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02529105321376424,"score_gpt":0.315626244481743,"score_spread":0.2903351912679787,"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."}}