{"id":"W4411267377","doi":"10.2139/ssrn.5288532","title":"Designing AI-Human Supervision to Improve Worker Performance: A Field Experiment in Service Operations","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Digital Transformation in Industry","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Field (mathematics); Service (business); Human services; Operations management; Computer science; Business; Engineering management; Process management; Knowledge management; Engineering; Marketing; Political science; Mathematics","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":[0.008899352,0.001045194,0.0006327418,0.0005107509,0.002144326,0.001115207,0.002192467,0.001884604,0.003882398],"category_scores_gemma":[0.01882262,0.0007315975,0.0004051543,0.0004362691,0.002305087,0.001233353,0.001388347,0.001917966,0.0008069797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001424997,"about_ca_system_score_gemma":0.004091045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004721201,"about_ca_topic_score_gemma":0.005593523,"domain_scores_codex":[0.9962041,0.002324816,0.0001652893,0.0005184506,0.0003351127,0.0004522619],"domain_scores_gemma":[0.9739954,0.01714815,0.001455417,0.002368428,0.001860115,0.003172492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","study_design_scores_codex":[0.06649134,0.3414721,0.06019067,0.003061886,0.0004560755,0.0007149481,0.04641896,0.06717209,0.1357102,0.004561455,0.006387547,0.2673628],"study_design_scores_gemma":[0.03742434,0.5041857,0.1589708,0.0004334499,0.0005951417,0.0003101312,0.02717558,0.1559172,0.08191309,0.01490645,0.01766025,0.0005078641],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992046,0.000016232,0.005643576,0.0001275628,0.00002788226,0.0008077453,0.00005394812,0.0001099513,0.001167007],"genre_scores_gemma":[0.9809375,0.00002850169,0.01637558,0.0001239497,0.00003161072,0.001028577,0.00008360305,0.00002265703,0.001368078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008899352,"threshold_uncertainty_score":0.04706478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229313164457681,"score_gpt":0.2669384212149841,"score_spread":0.2546452895704073,"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."}}