{"id":"W4414203932","doi":"10.1145/3767736","title":"Can Alternative Grading Improve Student Interactions in Automatically Graded Programming Assignments?","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Computing Education","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Grading (engineering); Debugging; Oracle; Formative assessment; Suite; Test suite; Unit testing; Software; Summative assessment; Software development","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":[0.0005495773,0.0002033878,0.0001915134,0.0006561014,0.0004940663,0.0004358261,0.0008912077,0.0000484002,0.000003706977],"category_scores_gemma":[0.0001502208,0.0002180256,0.00009076921,0.0009341828,0.00003368465,0.0002950088,0.00004199986,0.0007278741,0.000009339304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005811293,"about_ca_system_score_gemma":0.0003100254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005154557,"about_ca_topic_score_gemma":0.0001110596,"domain_scores_codex":[0.9981291,0.0002620311,0.000432702,0.0005480922,0.0002644766,0.0003635725],"domain_scores_gemma":[0.998533,0.0005125342,0.0001566927,0.0006332122,0.000082771,0.00008183661],"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":[0.000003189342,0.0008784441,0.001145724,0.00002469792,0.00004574419,0.000001325617,0.00708886,0.004025835,0.00009108742,0.00463108,0.00002325919,0.9820408],"study_design_scores_gemma":[0.005585421,0.001280954,0.1723937,0.006896132,0.0003360357,0.0001029832,0.02431908,0.6981384,0.008087094,0.03706843,0.0423821,0.003409715],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08835053,0.00002230438,0.9024407,0.005136226,0.002975898,0.0004328682,4.792673e-7,0.0004511131,0.0001898532],"genre_scores_gemma":[0.8075269,0.000001783291,0.1916557,0.0002863669,0.00004928759,0.00008716654,0.000003455616,0.00001109807,0.0003783131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.978631,"threshold_uncertainty_score":0.8890826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01910403271611229,"score_gpt":0.3473919119798712,"score_spread":0.328287879263759,"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."}}