{"id":"W4391054937","doi":"10.14778/3632093.3632096","title":"Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity Resolution","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Resource (disambiguation); Noise (video); Selection (genetic algorithm); Machine learning; Artificial intelligence; Resolution (logic); Data mining","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":[0.003901367,0.0001436617,0.0002423627,0.0001795661,0.0003503032,0.0002826864,0.0007780662,0.00007797755,0.00004904125],"category_scores_gemma":[0.002621769,0.00009840118,0.0001194163,0.0006834315,0.0001269927,0.0001866671,0.0007658761,0.000172585,0.00003171365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005115049,"about_ca_system_score_gemma":0.00001484993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005746144,"about_ca_topic_score_gemma":0.00002191001,"domain_scores_codex":[0.9976245,0.00002290538,0.0004909789,0.0004509359,0.001076907,0.0003338329],"domain_scores_gemma":[0.9986342,0.000460919,0.0003782885,0.00022708,0.0002149403,0.00008459172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003745844,0.0003127596,0.01692642,0.0005899199,0.0002528836,0.000001591037,0.01573699,0.0006259845,0.008565363,0.6782655,0.2192588,0.05908924],"study_design_scores_gemma":[0.001183177,0.0002653645,0.02241978,0.0003744437,0.0001122937,0.000003914199,0.01934921,0.003165946,0.01806594,0.4038255,0.5308076,0.0004268277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980651,0.00007711705,0.001106215,0.01115174,0.0002963744,0.00121489,0.000110326,0.0001435522,0.005248833],"genre_scores_gemma":[0.9870517,0.00005478143,0.003254167,0.0005706783,0.0001189527,0.0001367552,0.00001120574,0.00002100164,0.00878079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3115488,"threshold_uncertainty_score":0.4012684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07733140174241149,"score_gpt":0.3638194075327134,"score_spread":0.2864880057903019,"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."}}