{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008677314,0.0001252873,0.0001201963,0.0001386,0.0001593137,0.0007883029,0.0003441398,0.00004706718,0.00002294255],"category_scores_gemma":[0.0001530889,0.0001109968,0.00002008079,0.0005916263,0.00003803245,0.0008886441,0.0001790272,0.0001142184,0.0001050942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005969135,"about_ca_system_score_gemma":0.00005489304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008869094,"about_ca_topic_score_gemma":0.00005208848,"domain_scores_codex":[0.998396,0.00007954802,0.0002272236,0.0005012003,0.0005522775,0.0002437371],"domain_scores_gemma":[0.9989341,0.000137846,0.00007315318,0.0004010563,0.0003562945,0.00009747967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007664955,0.00008706367,0.008345808,0.00002645626,0.00002629734,0.000006009511,0.00484567,0.01756051,0.00979442,0.03845565,0.0001100909,0.9206654],"study_design_scores_gemma":[0.00007364,0.0003425087,0.01747539,0.0001624016,0.00002452784,0.00002598,0.0006886114,0.9127647,0.05651832,0.01103004,0.0005603354,0.0003335006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6046684,0.0000184545,0.3934365,0.0004783035,0.0003901289,0.0002912864,7.437214e-7,0.00008409961,0.0006320834],"genre_scores_gemma":[0.9962996,0.000002874053,0.003333023,0.0001954518,0.00007582911,0.00001842943,0.000003236275,0.000009584679,0.0000619491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9203319,"threshold_uncertainty_score":0.7601622,"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."}}