{"id":"W2742025582","doi":"10.1145/3077136.3080812","title":"Navigating Imprecision in Relevance Assessments on the Road to Total Recall","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Recall; Relevance (law); Computer science; Precision and recall; Ground truth; Relevance feedback; Information retrieval; Data curation; Data mining; Artificial intelligence; Image retrieval; Cognitive psychology; Psychology; Image (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":[0.05113214,0.001215882,0.002319789,0.004039424,0.001661306,0.009405167,0.00287371,0.003339622,0.001515848],"category_scores_gemma":[0.2605891,0.001657385,0.001459711,0.003564742,0.004684914,0.01413232,0.006382965,0.004898402,0.000615649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005198341,"about_ca_system_score_gemma":0.003182542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01849051,"about_ca_topic_score_gemma":0.0141949,"domain_scores_codex":[0.9436596,0.0396081,0.001934962,0.006022852,0.007652299,0.001122195],"domain_scores_gemma":[0.6957809,0.2653461,0.0100036,0.01688782,0.01095696,0.001024667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001326293,0.0002422795,0.02237577,0.0008515341,0.0003944431,0.0003026339,0.005400968,0.656076,0.002325234,0.1259279,0.005796807,0.1789803],"study_design_scores_gemma":[0.0002060624,0.0004962447,0.006386007,0.0003038433,0.0001294191,0.0003419392,0.001212345,0.6761714,0.003277535,0.3055755,0.005686436,0.0002131393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2673339,0.008727283,0.6939224,0.01120459,0.0001805218,0.000362225,0.0008792062,0.001701247,0.01568859],"genre_scores_gemma":[0.905555,0.000915951,0.09135923,0.0005495834,0.00005579988,0.0001840093,0.000261729,0.0001246351,0.0009939984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05113214,"threshold_uncertainty_score":0.2704158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.279431937892528,"score_gpt":0.534968558435086,"score_spread":0.255536620542558,"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."}}