{"id":"W4327586534","doi":"10.21203/rs.3.rs-2573085/v1","title":"Design and Evaluation of Crowd-sourcing Platforms Based on Users’ Confidence Judgments","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Correctness; Computer science; Test (biology); Metacognition; Popularity; Crowd sourcing; Artificial intelligence; Human–computer interaction; Machine learning; Cognition; Psychology; Social psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01378011,0.001624943,0.001174187,0.002094102,0.001259,0.00284592,0.002556106,0.002162445,0.003010033],"category_scores_gemma":[0.04201489,0.0009901847,0.0006991302,0.0009395097,0.001129634,0.003135749,0.002468561,0.001451744,0.001083857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001854033,"about_ca_system_score_gemma":0.002849365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003265044,"about_ca_topic_score_gemma":0.002110726,"domain_scores_codex":[0.990029,0.005509862,0.0005628582,0.00106675,0.002216668,0.0006148376],"domain_scores_gemma":[0.9589821,0.02351525,0.002772532,0.003120518,0.009012815,0.002596871],"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":[0.03775168,0.01896884,0.0618328,0.004227282,0.00118945,0.0009552988,0.005577198,0.1856605,0.182747,0.01783991,0.008778561,0.4744714],"study_design_scores_gemma":[0.002797411,0.0121901,0.01819338,0.0001548582,0.0004512238,0.0001582355,0.00165721,0.9018033,0.04922162,0.007986546,0.005109216,0.000276905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7457175,0.0003596781,0.2342004,0.000649897,0.0002413798,0.01008827,0.0004706505,0.001837052,0.006435215],"genre_scores_gemma":[0.8997682,0.00007821675,0.09507637,0.0001109576,0.00004482593,0.003124774,0.0002957922,0.00008717599,0.001413701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01378011,"threshold_uncertainty_score":0.07287711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2512312015292228,"score_gpt":0.4188936736434096,"score_spread":0.1676624721141868,"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."}}