{"id":"W4388408996","doi":"10.1109/dsaa60987.2023.10302571","title":"Towards Deep Learning Models for Automatic Computer Program Grading","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Python (programming language); Feature engineering; Leverage (statistics); Deep learning; Machine learning; Implementation; Grading (engineering); Compiler; Programming language; Software engineering","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":[0.001493959,0.001388351,0.0007665583,0.001272948,0.0002850039,0.001416704,0.001973792,0.001345395,0.002099688],"category_scores_gemma":[0.006650093,0.000589357,0.000782263,0.0008557934,0.0005248312,0.001737545,0.001217562,0.002907179,0.001565721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001504707,"about_ca_system_score_gemma":0.001269261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005963442,"about_ca_topic_score_gemma":0.01090556,"domain_scores_codex":[0.9992914,0.0002133941,0.00004312959,0.0001860152,0.0001742399,0.0000916975],"domain_scores_gemma":[0.9978008,0.0009245302,0.000229342,0.0002668868,0.0006725446,0.000105981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002157607,0.0003349175,0.00357997,0.0001620913,0.0001004139,0.00006108547,0.000120279,0.5128641,0.006502521,0.01019224,0.01297293,0.4528938],"study_design_scores_gemma":[0.000007247746,0.00002283539,0.0001605232,0.00001529735,0.000006652809,0.000005928004,0.00000644896,0.9917988,0.001311826,0.006100472,0.0005592154,0.000004782466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06133673,0.001082885,0.9222085,0.0008718434,0.0001269984,0.0001396364,0.0008575126,0.009723338,0.003652569],"genre_scores_gemma":[0.6074382,0.0005847506,0.3772971,0.0007047266,0.0001201209,0.0003661291,0.003996119,0.0005177202,0.008975072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005963442,"threshold_uncertainty_score":0.01185745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0649315470941495,"score_gpt":0.313413597167929,"score_spread":0.2484820500737795,"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."}}