{"id":"W4248501463","doi":"10.1002/spe.839","title":"Oto, a generic and extensible tool for marking programming assignments","year":2007,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Université du Québec à Montréal","keywords":"Computer science; Extensibility; Workload; Task (project management); Programming language; Automation; Process (computing); Software engineering; Source code; Code (set theory); Operating system; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001071178,0.0001674468,0.0001506782,0.00008916103,0.0003888928,0.0003799297,0.0002868794,0.00007298814,0.000001459414],"category_scores_gemma":[0.00451684,0.0001588738,0.00002800332,0.0002772978,0.00007500733,0.001317157,0.0002803906,0.0001177279,0.000001815293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003006896,"about_ca_system_score_gemma":0.00004063363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005233843,"about_ca_topic_score_gemma":0.00000113213,"domain_scores_codex":[0.9985194,0.00003508656,0.0002337246,0.0005373755,0.0002377661,0.0004367095],"domain_scores_gemma":[0.99721,0.002006775,0.0001590408,0.0003566458,0.0001478274,0.0001196661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004571157,0.00006968212,0.01357004,0.00004736858,0.00001208198,0.00005333772,0.005241741,7.350993e-7,0.0005017083,0.00107622,0.0008455975,0.9785358],"study_design_scores_gemma":[0.004333155,0.004361338,0.04231328,0.001540848,0.0002604579,0.006914927,0.006293019,0.02420013,0.03031593,0.08601283,0.7872845,0.006169579],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03249693,0.0007814121,0.9633939,0.0002073126,0.000159639,0.0003542087,7.717043e-7,0.002551355,0.00005443543],"genre_scores_gemma":[0.2614679,0.00005409787,0.7373871,0.0008843614,0.0000495958,0.0001179138,0.000001034076,0.00001189362,0.00002619547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9723662,"threshold_uncertainty_score":0.6478685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02826807852510816,"score_gpt":0.3206761770525451,"score_spread":0.292408098527437,"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."}}