{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004500676,0.001637915,0.001020337,0.001116398,0.001100064,0.002654257,0.002365106,0.00124841,0.005473481],"category_scores_gemma":[0.03136338,0.0008880854,0.001368767,0.001422378,0.00152255,0.004670586,0.002889805,0.003345067,0.001980633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279906,"about_ca_system_score_gemma":0.003016663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01075476,"about_ca_topic_score_gemma":0.01075441,"domain_scores_codex":[0.9948402,0.001254053,0.0004241217,0.001068332,0.001996442,0.000416957],"domain_scores_gemma":[0.9850804,0.007415986,0.0009362604,0.003090238,0.00290551,0.0005716162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00627827,0.001353246,0.03688915,0.004425387,0.0007113662,0.001536128,0.007073584,0.1625279,0.1844872,0.01990379,0.04048066,0.5343333],"study_design_scores_gemma":[0.0002552405,0.001122605,0.0125944,0.0002348786,0.0003636747,0.0006433264,0.00133508,0.7672414,0.1596857,0.01318157,0.04305657,0.0002856466],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3805762,0.001769949,0.4830311,0.001819948,0.0007396053,0.0004824916,0.002238651,0.1179248,0.01141741],"genre_scores_gemma":[0.7535071,0.0009244402,0.2189422,0.0006949689,0.00005577066,0.0004930392,0.003400725,0.01196668,0.01001521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01075476,"threshold_uncertainty_score":0.0238021,"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."}}