{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002109863,0.000128878,0.0001460271,0.0003491391,0.0003498598,0.0001805655,0.0003153091,0.0000448244,0.000001749879],"category_scores_gemma":[0.00007880873,0.0001045955,0.00002703546,0.0005653141,0.00001625134,0.0001703226,0.00002066114,0.000192897,0.000005676167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634405,"about_ca_system_score_gemma":0.0003553884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072124,"about_ca_topic_score_gemma":0.000005265269,"domain_scores_codex":[0.9980289,0.0003623484,0.0002556418,0.0003516008,0.0008300151,0.0001714595],"domain_scores_gemma":[0.9986888,0.0002191385,0.0001733544,0.0005096758,0.0003192949,0.0000897317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000218435,0.0002104562,0.0008228992,0.00005358245,0.00001564997,2.73817e-7,0.004303349,0.01822428,0.0006584492,0.00007584397,0.00002016126,0.9756129],"study_design_scores_gemma":[0.0007581497,0.001064233,0.4860415,0.00177847,0.0002646225,0.00002777105,0.005630019,0.5024297,0.001243846,0.00007962876,0.0003000408,0.0003819941],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6793813,0.00003768624,0.3186168,0.0004324217,0.0007533192,0.0005184422,4.435787e-7,0.0002428815,0.00001670544],"genre_scores_gemma":[0.934889,0.000003332449,0.06482495,0.00001406208,0.0000322578,0.0001314986,0.000004155569,0.00001177368,0.00008901809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9752309,"threshold_uncertainty_score":0.426528,"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."}}