{"id":"W2954631080","doi":"10.1016/j.artint.2019.03.004","title":"Incentivizing evaluation with peer prediction and limited access to ground truth","year":2019,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of Alberta; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Google","keywords":"Truth telling; Ground truth; Computer science; Incentive; Grading (engineering); Aggregate (composite); Set (abstract data type); Common ground; Artificial intelligence; Psychology; Social psychology","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":[0.02177766,0.001769723,0.003087352,0.001664601,0.001571298,0.003891914,0.003731072,0.005746175,0.005359698],"category_scores_gemma":[0.1051354,0.0009442304,0.0005838352,0.001588726,0.002641998,0.00766393,0.006142058,0.003400047,0.0015058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002445485,"about_ca_system_score_gemma":0.004380217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006016194,"about_ca_topic_score_gemma":0.00772548,"domain_scores_codex":[0.9792184,0.01086867,0.0007706442,0.003226798,0.004357944,0.001557504],"domain_scores_gemma":[0.8849922,0.08798803,0.004428139,0.0116035,0.007379163,0.003608946],"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":[0.007069752,0.002444671,0.02722765,0.0007513567,0.0005124039,0.0009917232,0.001312393,0.4523168,0.01679872,0.1212851,0.03774453,0.3315449],"study_design_scores_gemma":[0.0001921387,0.0002785946,0.002289706,0.00003716082,0.0000532162,0.00009996583,0.000133236,0.9140695,0.002857278,0.07733876,0.002604036,0.00004644478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2849378,0.002186725,0.6477429,0.01221169,0.001028883,0.001321742,0.0008736155,0.005124121,0.04457259],"genre_scores_gemma":[0.9774567,0.00007795297,0.01871188,0.0003828835,0.0001903988,0.00009633566,0.0001754027,0.0001005578,0.00280779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02177766,"threshold_uncertainty_score":0.1151726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06897691049487736,"score_gpt":0.3100311487303518,"score_spread":0.2410542382354744,"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."}}