{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001254146,0.0001391225,0.000125376,0.0008719358,0.0002844935,0.0007076623,0.00130068,0.00009109637,0.00005575741],"category_scores_gemma":[0.001227993,0.000124441,0.00001844148,0.0006151128,0.0001403402,0.001308989,0.0003563394,0.0002175282,0.000144471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000178599,"about_ca_system_score_gemma":0.0005552397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008947524,"about_ca_topic_score_gemma":0.000007802681,"domain_scores_codex":[0.997869,0.00003760466,0.000458967,0.0003586223,0.000893124,0.0003826857],"domain_scores_gemma":[0.9976265,0.0002310535,0.000127059,0.0004310545,0.001501203,0.00008306408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006287003,0.0007454381,0.01007964,0.0001290509,0.00004054185,0.000001287092,0.004149735,0.0000579541,0.0004827882,0.8789428,0.00569009,0.09905197],"study_design_scores_gemma":[0.006787441,0.00166678,0.02088727,0.0002422961,0.000003221081,0.00001088534,0.004130773,0.4969812,0.1156261,0.05442757,0.2980124,0.001224061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01734391,0.000009675084,0.9654049,0.006510507,0.0003431346,0.0008850237,0.00002313137,0.0001812752,0.009298472],"genre_scores_gemma":[0.8701008,0.000023829,0.1286783,0.0002068102,0.0000511578,0.0002157887,0.0002271876,0.000005090362,0.0004909944],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8527569,"threshold_uncertainty_score":0.6824003,"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."}}