{"id":"W4392721234","doi":"10.22318/icls2023.403455","title":"A Systematic Review of Automated Feedback Generation in Empirical Educational Research","year":2023,"lang":"en","type":"review","venue":"Proceedings.","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Empirical research; Quality (philosophy); Knowledge management","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":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01926065,0.0003143165,0.002465428,0.001140967,0.0000968087,0.00004120457,0.0004873922,0.0004025452,0.0003783329],"category_scores_gemma":[0.01241907,0.000245429,0.0002478468,0.00407187,0.0000999289,0.00005463434,0.00009693673,0.001623539,0.001143899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003241068,"about_ca_system_score_gemma":0.0004218399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002921725,"about_ca_topic_score_gemma":8.763263e-7,"domain_scores_codex":[0.9941394,0.002316042,0.001886686,0.0006166668,0.0006005159,0.0004407384],"domain_scores_gemma":[0.9967802,0.001181856,0.0009226974,0.0002692755,0.0007915691,0.00005438448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00000137114,0.00009734078,0.00001314626,0.9205323,0.0001482844,0.000001375476,0.0009797157,2.737328e-8,6.628218e-7,0.003741875,0.06742531,0.007058554],"study_design_scores_gemma":[0.00007680534,0.00005247261,0.00004371412,0.8733213,0.0002873346,0.00003727177,0.00009895895,0.0000515527,1.617441e-7,0.00005556021,0.125751,0.0002238623],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001499539,0.9852434,0.000004198165,0.0002009028,0.0003558676,0.002219428,0.000008146738,0.0001593476,0.01179366],"genre_scores_gemma":[0.000004908885,0.9904036,0.0008162889,0.000075927,0.0003927791,0.001719918,0.0001567865,0.00009111121,0.006338678],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.05832569,"threshold_uncertainty_score":0.9999998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5359588916240169,"score_gpt":0.616814941172234,"score_spread":0.08085604954821712,"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."}}