{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005145805,0.000129671,0.0001575843,0.0001830736,0.0002061735,0.0002827093,0.0005889346,0.00005338935,0.000002035084],"category_scores_gemma":[0.0001313288,0.0001129462,0.00008414521,0.0006243868,0.00002051436,0.0003134581,0.0002768472,0.0001036536,0.00002923743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002797137,"about_ca_system_score_gemma":0.00002834472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000233186,"about_ca_topic_score_gemma":9.119378e-7,"domain_scores_codex":[0.9988617,0.00003501924,0.0001878241,0.0003413639,0.0001940506,0.0003800571],"domain_scores_gemma":[0.9991103,0.0003665744,0.00005465427,0.0003124931,0.00008257246,0.0000733764],"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":[3.612458e-7,0.00001941429,0.0001597034,0.00003429998,0.000007525031,0.000004327748,0.0003719091,0.00352674,0.000002700942,0.01518291,0.008525637,0.9721645],"study_design_scores_gemma":[0.00008982265,0.000209251,0.0002393029,0.00003412778,0.000002750842,0.000009291718,0.00000342724,0.8427008,0.00005334529,0.1561794,0.0003403588,0.0001381314],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001946554,0.00001019088,0.9005631,0.0003108925,0.0001727956,0.0003555017,2.126249e-7,0.09595042,0.0006903813],"genre_scores_gemma":[0.2183715,0.000002087246,0.7810711,0.000125731,0.00005674068,0.0002071335,0.000004049034,0.00001510076,0.0001465013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9720263,"threshold_uncertainty_score":0.4605813,"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."}}