{"id":"W4244909627","doi":"10.1145/3381519","title":"Peer Prediction with Heterogeneous Users","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Economics and Computation","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Harvard School of Engineering and Applied Sciences; Google; National Science Foundation","keywords":"Computer science; Cluster analysis; Incentive; Robustness (evolution); Homogeneous; Limiting; Mechanism (biology); Incentive compatibility; Data mining; Machine learning; Artificial intelligence; Mathematics; Microeconomics","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":[0.00005986817,0.00009680833,0.00009324744,0.0000475959,0.000178922,0.0002039316,0.000134072,0.00003610518,0.00000247426],"category_scores_gemma":[0.00000434551,0.00009600599,0.00002908375,0.00009084561,0.00002348497,0.0002638992,0.000006393212,0.00008723968,0.00001005875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002345205,"about_ca_system_score_gemma":0.00002424341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001023091,"about_ca_topic_score_gemma":0.000007447141,"domain_scores_codex":[0.9993817,0.00001738686,0.0001312208,0.0002947994,0.00006710695,0.0001078115],"domain_scores_gemma":[0.9995885,0.00004302857,0.00004784277,0.0001732626,0.00005019148,0.0000971971],"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":[0.00002321586,0.00002134688,0.00004970529,0.000005825503,0.00002839127,0.000002302677,0.0009993429,0.7422773,0.00004322258,0.0003239765,0.00003260244,0.2561927],"study_design_scores_gemma":[0.000445489,0.0003577075,0.0005092536,0.000008151798,0.00001349878,0.00004606416,0.0000725905,0.9950483,0.001131621,0.0006938828,0.001536444,0.0001369941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2885917,0.000008656129,0.706369,0.004711193,0.00008217599,0.00006823906,0.000004208602,0.00009562758,0.00006928997],"genre_scores_gemma":[0.979386,0.000031625,0.01978922,0.000718629,0.00002967448,0.000006309404,0.000004369596,0.000009614416,0.0000245054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6907944,"threshold_uncertainty_score":0.3915011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01830308227507904,"score_gpt":0.2082043424436197,"score_spread":0.1899012601685406,"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."}}