{"id":"W4308789977","doi":"10.1145/3555223","title":"Teachable Conversational Agents for Crowdwork: Effects on Performance and Trust","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Crowdsourcing; Delegate; Computer science; Task (project management); Context (archaeology); Human–computer interaction; Workflow; Process (computing); Focus (optics); Conversation; Knowledge management; World Wide Web; Psychology; Engineering","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":[0.0003918915,0.0001521473,0.0001576444,0.0001474129,0.0008023311,0.0001748876,0.001053157,0.00003189912,0.000008617786],"category_scores_gemma":[0.00007778363,0.0001289784,0.00009043214,0.0001563436,0.00003178545,0.0003790249,0.0008489047,0.0002811186,0.000003121217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001347132,"about_ca_system_score_gemma":0.00001247634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006050109,"about_ca_topic_score_gemma":1.396925e-7,"domain_scores_codex":[0.9988365,0.00001770407,0.0002157658,0.0003913649,0.0003368479,0.0002018865],"domain_scores_gemma":[0.9990583,0.0001952955,0.0002697889,0.0003349177,0.0001038868,0.00003778847],"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":[0.001201733,0.001549594,0.02114083,0.002077372,0.0004767214,0.000004326292,0.02104853,0.01917495,0.0784189,0.1297096,0.2483718,0.4768257],"study_design_scores_gemma":[0.00322837,0.004253504,0.04595629,0.0008878225,0.00006528011,0.0001462336,0.0004052531,0.6986879,0.199883,0.008350252,0.03732663,0.0008094248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995059,0.000005294854,0.001372628,0.001081834,0.001284749,0.0003961589,0.00000163382,0.00007836313,0.0007203665],"genre_scores_gemma":[0.9946046,0.000001220796,0.003774211,0.0007377455,0.0002306089,0.00007966871,0.000001894758,0.00001406785,0.000555906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.679513,"threshold_uncertainty_score":0.6170963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03357795497916363,"score_gpt":0.2808237954090481,"score_spread":0.2472458404298845,"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."}}