{"id":"W2945134239","doi":"10.65109/ecst4444","title":"Report-Sensitive Spot-Checking in Peer-Grading Systems","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Grading (engineering); Computer science; Scalability; Incentive; Obstacle; Homogeneous; Ground truth; Theoretical computer science; Mathematical proof; Mathematics education; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0009314964,0.000101502,0.0001757093,0.000135234,0.0000417574,0.0001857266,0.0002846448,0.00004332261,0.00001173764],"category_scores_gemma":[0.00009959922,0.00008708759,0.00003981759,0.0003273167,0.000008130325,0.0002451268,0.0001366665,0.0002184523,0.0001873133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004360139,"about_ca_system_score_gemma":0.0000316836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008579506,"about_ca_topic_score_gemma":0.000009028508,"domain_scores_codex":[0.9987307,0.00007677159,0.0002370107,0.0003820953,0.0003239485,0.0002495378],"domain_scores_gemma":[0.9992636,0.0001003794,0.00009574344,0.000415615,0.00007245904,0.00005220979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001286995,0.0001861631,0.4332796,0.0002032316,0.0000766696,0.007518773,0.008074333,0.04436572,0.005263736,0.412374,0.002837972,0.08580695],"study_design_scores_gemma":[0.0002402737,0.00003331613,0.01448471,0.00008652298,0.000001251811,0.000567833,0.0002235135,0.9780533,0.0004533112,0.0002032238,0.005436563,0.0002161453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.509914,0.00005962412,0.3745852,0.001526114,0.002161309,0.0002539807,3.387203e-7,0.0004188886,0.1110805],"genre_scores_gemma":[0.9697158,8.128487e-7,0.01026489,0.00007852168,0.00008306058,0.000002587344,0.000001769962,0.000007076985,0.01984553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9336876,"threshold_uncertainty_score":0.3551329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01046836796641533,"score_gpt":0.25292207121072,"score_spread":0.2424537032443046,"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."}}