{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003182236,0.0001121047,0.0002597061,0.0001313808,0.0001926348,0.0001284415,0.0006698883,0.00003966344,0.000509096],"category_scores_gemma":[0.0006713736,0.00008964763,0.0001352558,0.0003380896,0.00009452448,0.0005183776,0.0002444771,0.0000930319,0.00009363797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003174878,"about_ca_system_score_gemma":0.00004302941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004675746,"about_ca_topic_score_gemma":0.0002099381,"domain_scores_codex":[0.9977359,0.0001382628,0.0006185799,0.0004524624,0.0007849727,0.0002698146],"domain_scores_gemma":[0.9983525,0.0004037612,0.0002024243,0.000731624,0.000220986,0.00008870682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000203912,0.0002687053,0.0001019578,0.00001181098,0.00002587343,6.475626e-7,0.0004963549,0.00005202502,0.0030856,0.02984739,0.08681764,0.8792716],"study_design_scores_gemma":[0.000514233,0.00006976581,0.001628487,0.00001189248,0.00004261374,0.000001912754,0.0004254377,0.03238667,0.01105852,0.353013,0.6006545,0.0001929299],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05438207,0.00002800752,0.9250962,0.008953398,0.0002658336,0.0006651781,0.0004954404,0.00006773457,0.01004615],"genre_scores_gemma":[0.6806998,0.00000883557,0.3159403,0.000767142,0.0004098911,0.00006636267,0.000037182,0.00001036554,0.002060178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8790787,"threshold_uncertainty_score":0.5574244,"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."}}