{"id":"W4366597152","doi":"10.1145/3591210","title":"Evaluation of Submission Limits and Regression Penalties to Improve Student Behavior with Automatic Assessment Systems","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Computing Education","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Grading (engineering); Computer science; Limiting; Mathematics education; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01638366,0.0009796059,0.0008332823,0.0007603912,0.0004845363,0.001521167,0.001859693,0.0008133042,0.001319844],"category_scores_gemma":[0.1080124,0.0003760474,0.0004438768,0.0005407311,0.0005347495,0.001495728,0.0008564342,0.001327101,0.0003348549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009291596,"about_ca_system_score_gemma":0.002305425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001738294,"about_ca_topic_score_gemma":0.001403387,"domain_scores_codex":[0.9827456,0.00973253,0.001824346,0.001153831,0.004110954,0.0004327399],"domain_scores_gemma":[0.8244206,0.1342057,0.01546268,0.006477922,0.01450582,0.004927306],"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":[0.02841952,0.03626708,0.1675929,0.001950958,0.000588396,0.0001639372,0.002470458,0.09079848,0.04947476,0.001123026,0.002468335,0.6186822],"study_design_scores_gemma":[0.00372697,0.1151422,0.2051833,0.0004095127,0.001004239,0.0002431133,0.001600905,0.597716,0.06748115,0.00159948,0.005568748,0.0003243747],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867365,0.0001168511,0.01096158,0.0001152244,0.00003997271,0.0005051533,0.0000547692,0.0005656159,0.0009043716],"genre_scores_gemma":[0.9749083,0.00007191402,0.02372146,0.0000790374,0.00001635596,0.000483351,0.000112971,0.00004303291,0.0005634861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01638366,"threshold_uncertainty_score":0.08664614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04838050288104476,"score_gpt":0.3938446937359261,"score_spread":0.3454641908548813,"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."}}