{"id":"W6948892139","doi":"10.5281/zenodo.10199473","title":"Avaliação da eficácia de mensagens de erro melhoradas geradas por Large Language Model em um curso introdutório de programação em Python","year":2023,"lang":"pt","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Evasion and Academic Success Factors","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Python (programming language); Suite; Order (exchange)","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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005311623,0.0004148106,0.0004151404,0.0005018505,0.004727431,0.002008408,0.002225719,0.0004500806,0.00990516],"category_scores_gemma":[0.002543657,0.0004560967,0.000214203,0.002356662,0.0002892341,0.0005091708,0.001658607,0.001185834,0.009301378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009979068,"about_ca_system_score_gemma":0.0001055713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000199748,"about_ca_topic_score_gemma":0.00005396444,"domain_scores_codex":[0.9933357,0.00184089,0.0005934117,0.000923231,0.00125132,0.002055487],"domain_scores_gemma":[0.9975236,0.0001055178,0.0003113532,0.0006731828,0.000469629,0.0009167148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001536934,0.0005153412,0.0001917078,0.0002445853,0.0001879729,0.0002345984,0.3587846,0.0005492413,0.01281909,0.007136387,0.5365515,0.08263133],"study_design_scores_gemma":[0.001101081,0.0002004314,0.0007003903,0.0001536268,0.0001126448,0.00005830339,0.1090607,0.03564132,0.001447161,0.0004886011,0.8502528,0.0007829726],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9550584,0.000526927,0.005036647,0.007576808,0.0005529943,0.001636331,0.001115215,0.004494281,0.0240024],"genre_scores_gemma":[0.9716599,0.0006533051,0.0003963625,0.0007158693,0.0006936833,5.192782e-7,0.001276372,0.002020843,0.02258318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3137013,"threshold_uncertainty_score":0.9997891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07463272552960565,"score_gpt":0.3454569173638374,"score_spread":0.2708241918342318,"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."}}