{"id":"W3106900815","doi":"","title":"To Train or Not to Train? How Training Affects the Diversity of Crowdsourced Data","year":2020,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Memorial University of Newfoundland","funders":"","keywords":"Training (meteorology); Diversity (politics); Crowdsourcing; Computer science; Training set; Data science; Artificial intelligence; World Wide Web; Geography","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":[0.003966872,0.0001089729,0.0003034936,0.0001112457,0.0004229054,0.0004926992,0.00188162,0.00006871396,5.766682e-7],"category_scores_gemma":[0.003137376,0.00006402454,0.0001507369,0.0006265493,0.00001040623,0.001455652,0.0004974971,0.0001664555,0.000004760479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001812821,"about_ca_system_score_gemma":0.0001466903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001027678,"about_ca_topic_score_gemma":0.00000542571,"domain_scores_codex":[0.9980339,0.0002090333,0.0005634943,0.0001025328,0.0008865701,0.0002045104],"domain_scores_gemma":[0.9967105,0.000579471,0.001650343,0.000422043,0.0004989912,0.0001386897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006032713,0.00005306647,0.001929188,0.0004591655,0.0006650674,0.000002461574,0.6378807,0.1016899,0.005634966,0.005362456,0.2002523,0.04546741],"study_design_scores_gemma":[0.006322003,0.001790316,0.02866853,0.00108457,0.0003545006,0.0001587378,0.08213704,0.4019354,0.006664541,0.00007522568,0.4698252,0.0009839364],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1979263,0.00001604628,0.7335483,0.06330646,0.002600977,0.001724743,0.0002002985,0.00007371876,0.0006031619],"genre_scores_gemma":[0.996201,6.410127e-7,0.001317237,0.002050087,0.0002402957,0.000003232061,0.000002844845,0.000005036698,0.0001795933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7982748,"threshold_uncertainty_score":0.4751109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08824991019651553,"score_gpt":0.2701563861884323,"score_spread":0.1819064759919168,"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."}}