{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001850914,0.00009349488,0.00009825453,0.0001761172,0.0001541774,0.0001116089,0.0002026837,0.0000768342,0.00004858846],"category_scores_gemma":[0.0001003907,0.00008316865,0.00001535298,0.0003391998,0.00002688549,0.0005152604,0.0001357391,0.0002751986,0.0001805727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001963746,"about_ca_system_score_gemma":0.00001832704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001388325,"about_ca_topic_score_gemma":0.00001624007,"domain_scores_codex":[0.9992599,0.00002740951,0.0001505871,0.0002843584,0.0001170223,0.0001606951],"domain_scores_gemma":[0.9993695,0.0002210656,0.00007935213,0.00024882,0.00005920171,0.00002206516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004028671,0.00001369896,0.0003509231,0.000003240976,0.00000706394,0.000002571824,0.0001466815,0.00003432144,0.002938201,0.9948856,0.0002843284,0.001329315],"study_design_scores_gemma":[0.001027392,0.0008818802,0.001708133,0.0001678462,0.000009988997,0.0001412254,0.00184004,0.6598946,0.1261638,0.2071806,0.0003816491,0.0006027581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2350877,0.00000157506,0.7513376,0.001146836,0.0007999178,0.0001166849,2.543583e-7,0.000262058,0.01124742],"genre_scores_gemma":[0.9905859,4.964244e-7,0.00858202,0.0003338503,0.00001714658,0.000005521701,0.000001063077,0.00000542197,0.000468572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7877051,"threshold_uncertainty_score":0.3391519,"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."}}