{"id":"W7126398324","doi":"10.21428/594757db.564cdb72","title":"Comparing Traditional and Deep Learning Approaches for Product Matching: Performance on Unseen Entities","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Deep learning; Feature learning; Autoencoder; Matching (statistics); Transformer; Representation (politics); Feature (linguistics); Training set","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":[0.005273521,0.001059009,0.0007566884,0.001727654,0.0004921059,0.001145729,0.001748809,0.001713308,0.002028192],"category_scores_gemma":[0.008958193,0.0002153289,0.0006958539,0.00175374,0.000576145,0.003913779,0.001992845,0.001401719,0.001337326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125396,"about_ca_system_score_gemma":0.000973836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006334553,"about_ca_topic_score_gemma":0.009054456,"domain_scores_codex":[0.9975554,0.000661387,0.0002120183,0.0006422481,0.0006137434,0.0003151667],"domain_scores_gemma":[0.9962529,0.001681946,0.0003281333,0.0009335711,0.0006277262,0.0001756646],"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":[0.001809117,0.0015206,0.04728297,0.000521446,0.0005389231,0.0002009289,0.000152893,0.240804,0.007871528,0.002407111,0.01176256,0.685128],"study_design_scores_gemma":[0.0000720911,0.0008995941,0.009062201,0.00006585263,0.00008027592,0.0001232329,0.0002184647,0.9631212,0.01894405,0.004263355,0.003110332,0.00003941386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9040287,0.004544829,0.075829,0.0008403925,0.0002710507,0.0001838827,0.002220915,0.003939888,0.008141345],"genre_scores_gemma":[0.9440903,0.0007607593,0.04581822,0.0002550245,0.0000595567,0.00005719832,0.005050253,0.0000874328,0.003821185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006334553,"threshold_uncertainty_score":0.02788937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4048250354532657,"score_gpt":0.3676819528872744,"score_spread":0.0371430825659913,"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."}}