{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000402465,0.000108896,0.0001110485,0.00007658352,0.0000866948,0.0004563411,0.000224295,0.00003663637,0.00005133138],"category_scores_gemma":[0.00001348693,0.00007409857,0.00002906958,0.0001789072,0.00001546277,0.0003327949,0.0001280328,0.0001712942,0.000104629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002603483,"about_ca_system_score_gemma":0.00004359831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004996476,"about_ca_topic_score_gemma":0.000003550478,"domain_scores_codex":[0.9989659,0.00002478811,0.0001259905,0.000372611,0.0002920046,0.0002187129],"domain_scores_gemma":[0.9996101,0.00006003307,0.00001735756,0.0001804688,0.00005509303,0.00007696092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[9.809046e-7,0.00000568544,0.0001192317,0.00002277466,0.00002379798,0.0001521844,0.0004891673,0.00001323937,0.0007279789,0.9811456,0.001145747,0.0161536],"study_design_scores_gemma":[0.0001898685,0.000480887,0.0003258131,0.0002886806,0.0000171419,0.0008676351,0.0003029851,0.2559798,0.004539796,0.002836436,0.7336524,0.0005185819],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003705246,0.00009343262,0.9883177,0.001196418,0.0005413273,0.00008740037,5.529809e-7,0.000343396,0.005714574],"genre_scores_gemma":[0.8884426,0.000005247654,0.03567402,0.0001104011,0.000205733,0.000007621109,8.974292e-7,0.00001469812,0.07553878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9783092,"threshold_uncertainty_score":0.4400508,"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."}}