{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007415856,0.00009468706,0.0001502963,0.00003686463,0.0004145646,0.001066525,0.001885297,0.00003413441,0.0004072247],"category_scores_gemma":[0.01038751,0.00005088559,0.00004575131,0.0001735461,0.00004290372,0.0005775288,0.001038703,0.0002140677,0.001683161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004173539,"about_ca_system_score_gemma":0.00001382401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006156237,"about_ca_topic_score_gemma":0.0005964389,"domain_scores_codex":[0.9974,0.0002125716,0.0004538247,0.0004673026,0.001246704,0.0002196045],"domain_scores_gemma":[0.9964469,0.001316704,0.0002010746,0.001898472,0.00006576088,0.00007107608],"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":[0.00002888326,0.00004585322,0.0007865547,7.766238e-7,0.00000260061,0.000005776194,0.0002002652,0.00008941829,0.0001414415,0.01090601,0.01924509,0.9685473],"study_design_scores_gemma":[0.001096059,0.0006023718,0.6450216,0.0004955743,0.000006714261,0.00000292187,0.005556049,0.01270352,0.002147366,0.1040869,0.2276541,0.0006268483],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8819772,0.000004122945,0.004722808,0.02071846,0.0005956476,0.0003709212,0.00001133516,0.00001974449,0.09157976],"genre_scores_gemma":[0.9857993,0.000005459599,0.002776078,0.002561696,0.00004253072,0.00002119767,0.000001555607,0.000004770049,0.008787408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9679205,"threshold_uncertainty_score":0.9999704,"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."}}