{"id":"W2894874337","doi":"10.1145/3209280.3232788","title":"The Quest for Total Recall","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Due diligence; Recall; Computer science; Categorization; Precision and recall; Haystack; Information retrieval; Government (linguistics); Enforcement; Data science; Knowledge management; Business; Psychology; Political science; World Wide Web; Finance; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00415833,0.00003270739,0.00004892385,0.00001952912,0.0002657209,0.00034296,0.0005320133,0.00001350333,0.0004468199],"category_scores_gemma":[0.002027077,0.00001480099,0.00003584403,0.0001145017,0.0001189132,0.0001423419,0.000168377,0.00001608913,0.001727344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005149197,"about_ca_system_score_gemma":0.00001025294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003288318,"about_ca_topic_score_gemma":0.0006506301,"domain_scores_codex":[0.9991068,0.00005193759,0.0001942947,0.0001711082,0.0003546214,0.0001213027],"domain_scores_gemma":[0.9982064,0.001115912,0.00003969696,0.0004719685,0.0001346423,0.00003135299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009602077,0.000006049787,0.000009742897,2.277712e-7,0.000002269919,6.081947e-8,0.00004578713,1.157889e-7,0.000006534371,0.3155506,0.5609186,0.1234504],"study_design_scores_gemma":[0.00006355399,0.00006094447,0.0005210438,5.791891e-7,0.000001306067,2.957031e-7,0.0004271542,0.0003749707,0.0001476633,0.09696545,0.9014091,0.00002792686],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.008079203,0.0000330808,0.261943,0.03929153,0.002278764,0.0004997203,0.00003549724,0.00007603997,0.6877632],"genre_scores_gemma":[0.4138443,0.00001061816,0.008253607,0.005469749,0.0007212573,0.00004369085,0.000006200858,0.000006334121,0.5716442],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4057651,"threshold_uncertainty_score":0.9990499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.316517329864422,"score_gpt":0.5082093572738737,"score_spread":0.1916920274094517,"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."}}