{"id":"W3121928352","doi":"","title":"Get Another Label? Improving Data Quality and Data Mining Using Multiple, Noisy Labelers","year":2008,"lang":"en","type":"article","venue":"The Faculty Digital Archive (New York University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Quality (philosophy); Sequence labeling; Set (abstract data type); Imperfect; Crowdsourcing; Artificial intelligence; Focus (optics); Outsourcing; Machine learning; Data quality; Data mining; Task (project management); Engineering; Operations management","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05628715,0.001906095,0.003796659,0.002852007,0.003051088,0.0061131,0.005679002,0.005722686,0.001955241],"category_scores_gemma":[0.20369,0.00185468,0.002314649,0.00408371,0.00648598,0.0169351,0.00849425,0.00672916,0.001585853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003267481,"about_ca_system_score_gemma":0.003679196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004048896,"about_ca_topic_score_gemma":0.005459627,"domain_scores_codex":[0.9503537,0.02573116,0.002402801,0.01028016,0.009889651,0.001342535],"domain_scores_gemma":[0.7609167,0.146386,0.01547831,0.05950804,0.01537152,0.002339518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003302162,0.001344522,0.05830147,0.002085162,0.001303989,0.000647222,0.00639865,0.1422854,0.02625489,0.0629131,0.01593962,0.6792238],"study_design_scores_gemma":[0.0003426763,0.0008195458,0.01019877,0.0004823944,0.0003879555,0.0008330804,0.001612748,0.6743777,0.0377869,0.2540003,0.01886679,0.000291116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05133817,0.001379395,0.9385371,0.004875813,0.000134682,0.0001687281,0.0003282013,0.001922385,0.001315541],"genre_scores_gemma":[0.364316,0.0005151551,0.6300961,0.001499507,0.000273666,0.0002869751,0.0008910986,0.0006470364,0.001474542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05628715,"threshold_uncertainty_score":0.2976785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2440212770188994,"score_gpt":0.3130783756742693,"score_spread":0.06905709865536985,"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."}}