{"id":"W4287817477","doi":"10.48550/arxiv.2004.02289","title":"Personalization in Human-AI Teams: Improving the Compatibility-Accuracy\\n Tradeoff","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Compatibility (geochemistry); Computer science; Personalization; Machine learning; World Wide Web; 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":[0.007508203,0.0009324356,0.0007305695,0.0007344938,0.001048194,0.002263742,0.001720764,0.001939113,0.002687445],"category_scores_gemma":[0.03732253,0.0007111114,0.0005611923,0.0005949921,0.00123934,0.005325649,0.003868873,0.00187355,0.0009100652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009034648,"about_ca_system_score_gemma":0.0009022076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00282284,"about_ca_topic_score_gemma":0.001979169,"domain_scores_codex":[0.9938149,0.003258097,0.0003271197,0.001219981,0.001076897,0.0003029717],"domain_scores_gemma":[0.9645167,0.01809007,0.003458645,0.01088959,0.001788086,0.001256889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002826583,0.00270821,0.0676095,0.0003094063,0.0002997283,0.000359135,0.00737353,0.2664766,0.03031927,0.01299475,0.002531433,0.6061919],"study_design_scores_gemma":[0.0002355678,0.002246603,0.0292748,0.00005813261,0.0001563558,0.0005615478,0.00136881,0.9043075,0.01975396,0.03627631,0.005626492,0.0001339424],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5897226,0.0003794885,0.3989908,0.0008239258,0.00005604142,0.0001989388,0.00004518688,0.001995462,0.007787594],"genre_scores_gemma":[0.9559956,0.00007463762,0.04251776,0.00008749438,0.00003215342,0.00005884075,0.00003728625,0.00007154552,0.001124703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007508203,"threshold_uncertainty_score":0.03970766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135238221238201,"score_gpt":0.2849147016041161,"score_spread":0.171390879480296,"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."}}