{"id":"W4387846873","doi":"10.1145/3583780.3615172","title":"Product Entity Matching via Tabular Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Serialization; ENCODE; Transformer; Data mining; Matching (statistics); Benchmark (surveying); Entity linking; Task (project management); Product (mathematics); Artificial intelligence; Information retrieval; Natural language processing; Machine learning; Knowledge base; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009536238,0.00006770335,0.0001248246,0.0001623914,0.0001407005,0.0004305808,0.002495494,0.00001444561,0.001912097],"category_scores_gemma":[0.001549569,0.00004730237,0.00002599685,0.001023261,0.0000357116,0.001119453,0.003177383,0.00006129738,0.01733996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006869638,"about_ca_system_score_gemma":0.00001622126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004140722,"about_ca_topic_score_gemma":0.000493516,"domain_scores_codex":[0.997511,0.0001334702,0.0003398416,0.0006553279,0.001157437,0.000202915],"domain_scores_gemma":[0.9967785,0.0002475733,0.0000673099,0.002799679,0.00005018683,0.00005678615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002667986,0.00003016912,0.0004774201,0.000006857473,0.00001210018,0.00001266932,0.0001340804,0.00003965023,0.0001860885,0.01673229,0.8778107,0.1045554],"study_design_scores_gemma":[0.00007051021,0.000005480013,0.005334572,0.000002615556,0.000005750599,6.258655e-7,0.0007768648,0.002708438,0.0001594035,0.1040865,0.8867544,0.00009485109],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1604108,0.0001314829,0.6651023,0.04732496,0.004828068,0.001147158,0.0006606304,0.001559358,0.1188353],"genre_scores_gemma":[0.8474625,0.00006088258,0.009269536,0.002586959,0.0003888978,0.00001269406,0.0009611046,0.00001896373,0.1392384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6870518,"threshold_uncertainty_score":0.9990003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4807826226288973,"score_gpt":0.492133428387495,"score_spread":0.01135080575859776,"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."}}