{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007400271,0.0008808672,0.0007300694,0.0005667993,0.00209197,0.002807823,0.001191971,0.001630265,0.005223569],"category_scores_gemma":[0.07379197,0.0004641527,0.0004680449,0.0003848073,0.001757605,0.002391808,0.003360072,0.001957101,0.001238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001393298,"about_ca_system_score_gemma":0.001598625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006929149,"about_ca_topic_score_gemma":0.004922952,"domain_scores_codex":[0.9941452,0.003579465,0.0003148258,0.0007019044,0.0007047456,0.000553821],"domain_scores_gemma":[0.9186814,0.05989667,0.006141536,0.006183843,0.003354126,0.005742448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02973894,0.01676687,0.1451962,0.00301044,0.001021122,0.002681012,0.06340561,0.1834151,0.08585306,0.01322958,0.01362209,0.44206],"study_design_scores_gemma":[0.00406823,0.03404392,0.2058726,0.0008694983,0.001102521,0.001028235,0.05683609,0.5627441,0.05636793,0.03731431,0.03886237,0.0008901365],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854283,0.0001957734,0.006751696,0.0005914816,0.00005915396,0.0001782223,0.0001072657,0.0004893471,0.006198816],"genre_scores_gemma":[0.9959069,0.00005760019,0.002523261,0.00005790455,0.00001272693,0.0001109307,0.00006449605,0.00004985138,0.00121631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007400271,"threshold_uncertainty_score":0.03913689,"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."}}