{"id":"W2943082885","doi":"10.1145/3290607.3312764","title":"Understanding and Correcting Inaccurate Calorie Estimations on Amazon Mechanical Turk","year":2019,"lang":"en","type":"article","venue":"","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; University of Toronto","keywords":"Calorie; Computer science; Tracking (education); Energy (signal processing); Amazon rainforest; Contrast (vision); Psychology; Data science; Applied psychology; Artificial intelligence; Statistics; Mathematics; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003689616,0.001010642,0.0005225535,0.0008368045,0.0006601816,0.001430337,0.0009745869,0.000796744,0.006747469],"category_scores_gemma":[0.04079419,0.0002800243,0.0003520192,0.0005147444,0.0003173127,0.001244836,0.001089861,0.0004548897,0.003042955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003471398,"about_ca_system_score_gemma":0.0007600706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003473434,"about_ca_topic_score_gemma":0.006201604,"domain_scores_codex":[0.9940718,0.003349372,0.0005095199,0.0006382096,0.001180629,0.0002503761],"domain_scores_gemma":[0.9769558,0.0140763,0.002376643,0.002140233,0.004171036,0.0002800193],"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":[0.002734845,0.001287736,0.1330265,0.002255735,0.000302475,0.001345084,0.01607238,0.006067048,0.04002268,0.002134952,0.03967545,0.7550751],"study_design_scores_gemma":[0.000533413,0.00286789,0.6270376,0.001407313,0.0006683152,0.001451008,0.02709635,0.1378501,0.065146,0.0161574,0.1189109,0.0008737838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.905259,0.0006217539,0.063352,0.001872652,0.0003252353,0.001229425,0.00288735,0.004164084,0.02028837],"genre_scores_gemma":[0.9484317,0.0002433748,0.04486221,0.000410351,0.0001157066,0.0007697879,0.001048158,0.0001840523,0.003934785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006747469,"threshold_uncertainty_score":0.02257246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125595171316818,"score_gpt":0.2943669579840534,"score_spread":0.1818074408523716,"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."}}