{"id":"W2745758802","doi":"10.1145/3105726.3106173","title":"RoboBUG","year":2017,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Computer science; Confusion; Task (project management); Human–computer interaction; Face (sociological concept); Programming language; Multimedia; Software engineering; Psychology; 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":[0.0001643503,0.00002795061,0.00003008441,0.00001182689,0.0004534598,0.0006002514,0.000900264,0.00001234729,0.00001263296],"category_scores_gemma":[0.00006459095,0.00002223462,0.00001779914,0.000009796425,0.00001444946,0.0002685988,0.0001816215,0.00007087992,0.0001104762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003137346,"about_ca_system_score_gemma":0.00000653403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167193,"about_ca_topic_score_gemma":0.000005843651,"domain_scores_codex":[0.9996982,0.00001139753,0.00003129326,0.0001057326,0.00005781599,0.00009562352],"domain_scores_gemma":[0.9992958,0.00001054793,0.00002757573,0.0006292894,0.000007342695,0.00002939399],"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":[9.593526e-8,0.000005044993,0.003607072,5.666027e-7,0.000001321925,0.000003066357,0.0001626532,0.000008490682,0.00001041076,0.09999665,0.0007095759,0.8954951],"study_design_scores_gemma":[0.0001228476,0.00002599083,0.0702141,0.000006392373,8.402443e-7,0.000009368223,0.000009306801,0.008349589,0.0001454929,0.0008979767,0.9201042,0.0001138636],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002846977,0.0000120073,0.9510054,0.003200112,0.0002470981,0.00001447005,8.656651e-9,0.0003191889,0.04235473],"genre_scores_gemma":[0.7667194,3.39521e-7,0.2277972,0.00007506179,0.00002843022,7.84421e-7,3.644583e-8,0.000001350281,0.005377411],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9193947,"threshold_uncertainty_score":0.5788239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611003969271973,"score_gpt":0.2924298965014008,"score_spread":0.2663198568086811,"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."}}