{"id":"W2941931605","doi":"","title":"Duplicate Removal for Overlapping Clusters: A Study Using Social Media Data.","year":2019,"lang":"en","type":"article","venue":"AAAI Spring Symposium Combining Machine Learning with Knowledge Engineering","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Social media; Computer science; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001616326,0.0005724147,0.0007966809,0.000446959,0.0004720794,0.0005401591,0.002014541,0.0001323982,0.000005703846],"category_scores_gemma":[0.0001982965,0.000555226,0.0001727506,0.0007840035,0.00002874706,0.0008205466,0.001326727,0.0009282606,0.00003404878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00018453,"about_ca_system_score_gemma":0.0001167746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005024092,"about_ca_topic_score_gemma":0.00004745029,"domain_scores_codex":[0.9964788,0.0001451567,0.0006758183,0.001342013,0.000456685,0.0009015486],"domain_scores_gemma":[0.9977774,0.0007505901,0.0003429984,0.0007872445,0.000189147,0.0001526191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008474676,0.0004082192,0.009088945,0.0003731373,0.0008185139,0.00007099791,0.02775388,0.9331004,0.004825135,0.02041741,0.00002258305,0.00303603],"study_design_scores_gemma":[0.001858211,0.0002475921,0.0006703003,0.0003113647,0.0001298181,0.00005277218,0.0004116944,0.9940543,0.00004121283,0.000001325772,0.001512969,0.0007083929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5172877,0.000174677,0.4803572,0.00005969024,0.0007819885,0.0004756449,0.000002024208,0.0006584664,0.0002026171],"genre_scores_gemma":[0.9692178,0.000002530544,0.03000937,0.00001747196,0.0004004833,0.00002632641,0.00002543346,0.0001297707,0.0001707871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4519301,"threshold_uncertainty_score":0.9996899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01923810525571718,"score_gpt":0.249872969439877,"score_spread":0.2306348641841598,"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."}}