{"id":"W2460936583","doi":"10.1145/2911451.2914709","title":"Impact of Review-Set Selection on Human Assessment for Text Classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Selection (genetic algorithm); Relevance (law); Context (archaeology); Computer science; Sampling (signal processing); Set (abstract data type); Information retrieval; Data mining; Statistics; Machine learning; Artificial intelligence; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2180206,0.001254036,0.001817559,0.003524964,0.002376452,0.004043072,0.001526047,0.001976927,0.003509198],"category_scores_gemma":[0.6559159,0.0006740594,0.002290085,0.002286826,0.002493966,0.004166143,0.002991984,0.001894369,0.001450751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002119803,"about_ca_system_score_gemma":0.002859781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00254061,"about_ca_topic_score_gemma":0.003838722,"domain_scores_codex":[0.5992012,0.3084759,0.02406472,0.01954944,0.04675849,0.001950151],"domain_scores_gemma":[0.1529107,0.7755997,0.03446464,0.01735913,0.01696014,0.00270584],"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":[0.03479267,0.001692137,0.3514674,0.005721209,0.005219914,0.001105709,0.01267353,0.00424608,0.02551807,0.00161982,0.01417715,0.5417665],"study_design_scores_gemma":[0.003019329,0.01938011,0.839402,0.003184443,0.006638006,0.007691348,0.005968912,0.03846473,0.03442347,0.01237254,0.02823017,0.001224763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8921064,0.01833516,0.05305211,0.005079225,0.00180005,0.003577992,0.0009110024,0.001447643,0.02369045],"genre_scores_gemma":[0.9812367,0.0008325888,0.01381951,0.001087693,0.0003654494,0.0006576076,0.0003596248,0.0001603164,0.001480566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2180206,"threshold_uncertainty_score":0.9643198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05918482990337513,"score_gpt":0.4245141933815084,"score_spread":0.3653293634781332,"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."}}