{"id":"W2941695365","doi":"10.48550/arxiv.1904.10403","title":"Optimizing Search API Queries for Twitter Topic Classifiers Using a Maximum Set Coverage Approach","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Classifier (UML); Information retrieval; Set (abstract data type); Precision and recall; Data mining; Training set; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004208914,0.002017071,0.003341847,0.003085872,0.001037905,0.002513791,0.002551275,0.002313009,0.002331266],"category_scores_gemma":[0.01654881,0.0008017229,0.001822158,0.003374843,0.0009890514,0.003624047,0.002095058,0.001819818,0.001040326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002194549,"about_ca_system_score_gemma":0.001928587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006529189,"about_ca_topic_score_gemma":0.007223125,"domain_scores_codex":[0.9967817,0.001067616,0.00029893,0.0006699312,0.0008449484,0.0003367827],"domain_scores_gemma":[0.9911265,0.00674269,0.0005135478,0.0006213846,0.0007966456,0.0001991964],"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":[0.001394598,0.0009421638,0.01067857,0.0006993733,0.0003012606,0.000381996,0.0008447371,0.4070549,0.01605285,0.008797629,0.01817083,0.5346811],"study_design_scores_gemma":[0.0000326678,0.0001028537,0.0006303522,0.00001284712,0.00003413381,0.00006268865,0.0001176184,0.9905794,0.00220002,0.005263858,0.0009506859,0.00001286221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1045878,0.002348481,0.8830528,0.001314179,0.00007269323,0.0004772372,0.001149395,0.004145332,0.00285198],"genre_scores_gemma":[0.664034,0.0007238157,0.3250329,0.0006554638,0.0004609348,0.0008875246,0.003693446,0.0006957386,0.00381616],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006529189,"threshold_uncertainty_score":0.02225912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2023589357258472,"score_gpt":0.2432152504124623,"score_spread":0.0408563146866151,"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."}}