{"id":"W6997218280","doi":"","title":"A Weighted-Tree Simplicity Algorithm for Similarity Matching of Partial Product Descriptions","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simplicity; Tree (set theory); Matching (statistics); Similarity (geometry); Product (mathematics); Measure (data warehouse); Simple (philosophy); Order (exchange)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.002628544,0.0005124803,0.00113795,0.003215382,0.0009556981,0.00153819,0.002212641,0.001424135,0.003501508],"category_scores_gemma":[0.01362331,0.0004797497,0.001170729,0.004234428,0.0007005713,0.004410297,0.002534952,0.001078521,0.001103411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001357379,"about_ca_system_score_gemma":0.001787903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002047362,"about_ca_topic_score_gemma":0.002945698,"domain_scores_codex":[0.9975321,0.0005941702,0.0002714139,0.0004842086,0.0009850217,0.0001331034],"domain_scores_gemma":[0.9958312,0.001749324,0.000481084,0.0009600419,0.0008239106,0.0001544936],"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":[0.0003478239,0.0002310827,0.004148141,0.0002714952,0.0001402818,0.0001351446,0.0003710253,0.08741693,0.009501965,0.0649051,0.005932643,0.8265985],"study_design_scores_gemma":[0.00008343004,0.0001746281,0.001302431,0.0000324037,0.00005998493,0.0004188782,0.0000990641,0.8987125,0.006874163,0.08512419,0.007077146,0.0000410566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01471521,0.0001071398,0.9830847,0.00009829326,0.00001585927,0.000190206,0.0001621537,0.0005703961,0.001055947],"genre_scores_gemma":[0.09565084,0.00008111769,0.9024892,0.00006675207,0.00001731167,0.0001652338,0.0005702709,0.00009316114,0.0008661238],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003501508,"threshold_uncertainty_score":0.01390129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1405199667415054,"score_gpt":0.3890718620059818,"score_spread":0.2485518952644764,"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."}}