{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003803697,0.001698723,0.001085408,0.003966409,0.000683181,0.002670032,0.002922651,0.001254127,0.01462466],"category_scores_gemma":[0.02413392,0.00112853,0.0009022567,0.002101902,0.001015456,0.003903323,0.003639865,0.001472902,0.004523473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006017946,"about_ca_system_score_gemma":0.00181269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00118976,"about_ca_topic_score_gemma":0.001078234,"domain_scores_codex":[0.9967894,0.0005967392,0.000625644,0.0004901334,0.001241791,0.0002563182],"domain_scores_gemma":[0.9866519,0.006301859,0.001556584,0.002811627,0.001529854,0.001148255],"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":[0.00112179,0.0007291697,0.00590648,0.001490507,0.00008183363,0.001570052,0.001856919,0.008382333,0.03824449,0.0134629,0.05335064,0.873803],"study_design_scores_gemma":[0.001410539,0.001449659,0.01615257,0.00175217,0.0002898716,0.006858051,0.00105755,0.1909157,0.1101387,0.04833864,0.6207331,0.0009034106],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01696551,0.0002289373,0.8483173,0.0002111102,0.0002558602,0.001039641,0.00148433,0.1247445,0.006752818],"genre_scores_gemma":[0.1095949,0.0005623594,0.8510106,0.0002825736,0.0001553393,0.001332914,0.00656477,0.01601022,0.01448639],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01462466,"threshold_uncertainty_score":0.04892433,"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."}}