{"id":"W2022780779","doi":"10.5539/cis.v4n6p48","title":"Semi-Automatic Labeling of Training Data Sets in Text Classification","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Carelessness; Computer science; Set (abstract data type); Training set; Process (computing); Reduction (mathematics); Data set; Data mining; Data reduction; Information retrieval; Artificial intelligence; Labeled data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009224695,0.00007412874,0.0001074879,0.0005107431,0.00009805045,0.0001740812,0.001702568,0.00003540204,0.000005535528],"category_scores_gemma":[0.00008698011,0.00006564394,0.000008894547,0.001144739,0.0002418212,0.01320285,0.000663743,0.00007260274,0.00001513654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002078393,"about_ca_system_score_gemma":0.0001120341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008525418,"about_ca_topic_score_gemma":9.38638e-7,"domain_scores_codex":[0.9989117,0.00001491651,0.0004181449,0.0002132759,0.0002757416,0.0001661812],"domain_scores_gemma":[0.9988643,0.00004362968,0.0002132172,0.0007269015,0.0001093437,0.00004261531],"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":[7.830556e-7,0.00001586385,0.00165569,0.00002096768,0.000001277592,1.813256e-7,0.007845432,0.00001191104,0.0003430053,0.08522769,0.00007534465,0.9048018],"study_design_scores_gemma":[0.0001741018,0.00003125781,0.1002965,0.00003634436,0.000001044062,0.000006035033,0.000583965,0.8954082,0.001164904,0.001787538,0.0004127713,0.00009735397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1339609,0.00003785998,0.8600116,0.00032206,0.000240123,0.0001884232,0.000003520103,0.0002510984,0.004984445],"genre_scores_gemma":[0.8671703,0.00003038503,0.1326653,0.000118799,0.000003522255,0.000004190774,0.000004752513,0.000001025533,0.000001753422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9047045,"threshold_uncertainty_score":0.9571744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1389177259685581,"score_gpt":0.3032114196743241,"score_spread":0.164293693705766,"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."}}