{"id":"W4382239954","doi":"10.1609/aaai.v37i5.25757","title":"Better Peer Grading through Bayesian Inference","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Institute for the Theory of Computing, University of California Berkeley; Alberta Machine Intelligence Institute; Compute Canada; Defense Advanced Research Projects Agency; University of British Columbia; Canadian Institute for Advanced Research","keywords":"Grading (engineering); Computer science; Inference; Interpretability; Rubric; Robustness (evolution); Machine learning; Bayesian probability; Probabilistic logic; Bayesian inference; Artificial intelligence; Mathematics; Mathematics education","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":[0.01634049,0.001118933,0.001911437,0.00247284,0.00130656,0.004195146,0.002402949,0.001909368,0.003969164],"category_scores_gemma":[0.07992797,0.0007547569,0.0008858821,0.001828158,0.0009044791,0.006357613,0.002585785,0.002833151,0.001619994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002254368,"about_ca_system_score_gemma":0.00209155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277591,"about_ca_topic_score_gemma":0.01268861,"domain_scores_codex":[0.9860292,0.007815825,0.0006185049,0.002163753,0.00292386,0.0004488328],"domain_scores_gemma":[0.9706959,0.01760876,0.002476295,0.004515661,0.004167813,0.0005355361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003974903,0.0004713681,0.01727685,0.0002167885,0.0003279208,0.0001659962,0.001315585,0.5361344,0.002478501,0.06013022,0.01154166,0.3695432],"study_design_scores_gemma":[0.00003603278,0.00004392243,0.001760459,0.00001975761,0.00003076083,0.00002634648,0.00008436505,0.944091,0.0009885399,0.05059536,0.002288517,0.00003510033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07000143,0.0004583084,0.9177708,0.00165925,0.0001182694,0.0001858198,0.0003591377,0.002493219,0.00695367],"genre_scores_gemma":[0.7929531,0.0002443527,0.2001951,0.0003458302,0.0001639179,0.0001625824,0.0005341604,0.0003013735,0.005099591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01634049,"threshold_uncertainty_score":0.08641785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07531137878603723,"score_gpt":0.3286441539662129,"score_spread":0.2533327751801757,"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."}}