{"id":"W7125351318","doi":"","title":"A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Undergraduate Education; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"CLARITY; Technical writing; Perspective (graphical); Preference; Course (navigation); Scalability; Quality (philosophy); Peer feedback","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01759024,0.0004292469,0.000639597,0.002310795,0.001093484,0.003213119,0.0004920048,0.0008023695,0.001466463],"category_scores_gemma":[0.07966901,0.0003016401,0.0005136878,0.001183546,0.001499576,0.001496893,0.002240388,0.001150018,0.0003004324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108011,"about_ca_system_score_gemma":0.00109363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008510894,"about_ca_topic_score_gemma":0.001102472,"domain_scores_codex":[0.982859,0.009921047,0.001143069,0.0008233512,0.004320545,0.0009330238],"domain_scores_gemma":[0.8997066,0.06390364,0.0139049,0.001630452,0.01525733,0.005597118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001137311,0.001254437,0.4117295,0.0005287578,0.0001548595,0.0005262716,0.482664,0.0004128666,0.01399976,0.0005172123,0.001032913,0.08604208],"study_design_scores_gemma":[0.00009926449,0.005956407,0.4996724,0.0004508672,0.0001360428,0.0006947893,0.4741456,0.003140667,0.00899986,0.0005871411,0.005919386,0.000197518],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987416,0.00005245984,0.0004784969,0.0000851073,0.000007468248,0.00001464839,0.00001482973,0.000009956102,0.0005954684],"genre_scores_gemma":[0.9991234,0.00006157756,0.0004341488,0.00005832493,0.000008428008,0.0000289839,0.00002295099,0.000008271722,0.000253918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01759024,"threshold_uncertainty_score":0.09302717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1714072170295567,"score_gpt":0.5004576099750087,"score_spread":0.3290503929454519,"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."}}