{"id":"W4392564502","doi":"10.1145/3626252.3630891","title":"Mechanical TA 2: Peer Grading with TA and Algorithmic Support","year":2024,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Grading (engineering); Computer science; Inference; Peer-to-peer; Artificial intelligence; Distributed computing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006575088,0.0009104502,0.001095219,0.001929622,0.001172549,0.003774865,0.004092928,0.001332267,0.02395096],"category_scores_gemma":[0.04167829,0.00056469,0.0007142611,0.00189356,0.0006909246,0.003386732,0.004473401,0.001614155,0.01196352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008580384,"about_ca_system_score_gemma":0.003104008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002614901,"about_ca_topic_score_gemma":0.003977231,"domain_scores_codex":[0.9883655,0.004012391,0.0006999352,0.001584445,0.004738221,0.000599435],"domain_scores_gemma":[0.9627247,0.009744728,0.003176537,0.01282913,0.009067074,0.00245792],"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":[0.0009884678,0.001122181,0.006099379,0.0003379288,0.0001222332,0.0001805788,0.0005234108,0.01499315,0.01128378,0.02193788,0.07726328,0.8651477],"study_design_scores_gemma":[0.001387689,0.002269188,0.01685438,0.0001502601,0.0001596729,0.0009080012,0.0003336256,0.6710258,0.02969527,0.06523354,0.2116165,0.0003660129],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07694644,0.0004100082,0.795963,0.0009481137,0.0008442745,0.001495214,0.0009735897,0.08002365,0.04239562],"genre_scores_gemma":[0.4538532,0.0001527346,0.4992723,0.000366454,0.0006689884,0.0008241064,0.001743842,0.003930283,0.03918821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02395096,"threshold_uncertainty_score":0.08012396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01561436196216439,"score_gpt":0.2443605334160499,"score_spread":0.2287461714538855,"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."}}