{"id":"W4401436150","doi":"10.1038/s41598-024-65892-7","title":"Design and evaluation of crowdsourcing platforms based on users’ confidence judgments","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Crowdsourcing; Computer science; Correctness; Popularity; Metacognition; Test (biology); Data science; Cognition; Artificial intelligence; World Wide Web; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00850988,0.0001443866,0.0001595707,0.0003491378,0.0002658754,0.001018223,0.0002059229,0.00005752235,0.0000197168],"category_scores_gemma":[0.0002151035,0.0001215802,0.00005685668,0.0006797274,0.0001645876,0.0004698454,0.000080795,0.0001161887,0.000009966119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007549235,"about_ca_system_score_gemma":0.0004003498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308273,"about_ca_topic_score_gemma":0.000001580083,"domain_scores_codex":[0.9970119,0.0000846779,0.0004294493,0.0008933642,0.001322871,0.0002577538],"domain_scores_gemma":[0.9983072,0.0001984274,0.0001738683,0.0009597377,0.0002611436,0.00009959386],"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":[0.00003227698,0.0002257261,0.001856158,0.0004879016,0.00009470028,0.001121262,0.01075496,0.5427569,0.2063683,0.007349827,0.0105509,0.218401],"study_design_scores_gemma":[0.0001024561,0.00004755235,0.0002314367,0.0004254273,0.00002459466,0.0001044471,0.00004287133,0.9065645,0.0793882,0.01256785,0.0003640992,0.0001365457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4934978,0.0002581542,0.5009054,0.0000798735,0.004186607,0.0003617933,2.611814e-7,0.0001455814,0.0005645121],"genre_scores_gemma":[0.9902037,9.10932e-7,0.009500433,0.00003299259,0.0000219543,0.00001512083,0.000002806775,0.00001041712,0.0002116776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4967059,"threshold_uncertainty_score":0.9818751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04520563480979342,"score_gpt":0.283899460839972,"score_spread":0.2386938260301786,"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."}}