{"id":"W2918429485","doi":"","title":"A Best Match KNN-based Approach for Large-scale Product Categorization.","year":2018,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Trent University; York University","funders":"","keywords":"Categorization; Computer science; Scale (ratio); Product (mathematics); Artificial intelligence; Data mining; Pattern recognition (psychology); Mathematics; Cartography; Geography","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":[0.002884294,0.001921872,0.002536625,0.008502367,0.002171953,0.002647227,0.005112526,0.003788165,0.00950366],"category_scores_gemma":[0.007569421,0.0007619867,0.002344518,0.008130332,0.0008419373,0.003727709,0.002841388,0.00205452,0.008303275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001588674,"about_ca_system_score_gemma":0.002714912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01827435,"about_ca_topic_score_gemma":0.03431482,"domain_scores_codex":[0.9958288,0.0006380704,0.0004042907,0.001273159,0.001453079,0.0004026004],"domain_scores_gemma":[0.9973404,0.0007613832,0.0001781155,0.0005251582,0.001013276,0.0001816673],"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":[0.0008894078,0.001092354,0.005861633,0.0004697011,0.0006429152,0.000314413,0.0001919283,0.02693512,0.007303566,0.003873795,0.05806817,0.8943569],"study_design_scores_gemma":[0.0001259539,0.0003029327,0.004248111,0.0001126842,0.0003103124,0.0004999885,0.0005733126,0.9394288,0.005514711,0.02996639,0.0188444,0.00007234551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04874412,0.005751807,0.9065855,0.001026754,0.0009699687,0.001745456,0.007196938,0.01473832,0.01324116],"genre_scores_gemma":[0.2256925,0.0007192221,0.7427307,0.0007827271,0.0003044991,0.0005813919,0.01388176,0.0005544599,0.0147527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01827435,"threshold_uncertainty_score":0.03633595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09819718700532777,"score_gpt":0.3537909891693088,"score_spread":0.2555938021639811,"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."}}