{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006412088,0.001559198,0.001671174,0.001283198,0.001252711,0.00196231,0.00540076,0.003455935,0.003134022],"category_scores_gemma":[0.01055502,0.0009331186,0.0009244023,0.00137474,0.001828185,0.006155999,0.005761973,0.004021928,0.001864594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111135,"about_ca_system_score_gemma":0.002158785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004745875,"about_ca_topic_score_gemma":0.007418619,"domain_scores_codex":[0.9966414,0.001270042,0.0001233418,0.001002536,0.0006105563,0.0003521615],"domain_scores_gemma":[0.9957962,0.001886054,0.0003807282,0.0009946006,0.000655569,0.0002868274],"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":[0.0006967189,0.0008197749,0.006063588,0.0001887338,0.0002595687,0.0004500094,0.0009282542,0.4115335,0.007687685,0.03831386,0.01171902,0.5213392],"study_design_scores_gemma":[0.00002345727,0.00007619999,0.0002378688,0.00001307776,0.00003439523,0.00007893422,0.00005570249,0.9795758,0.003080169,0.01419246,0.002612479,0.00001954139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0135164,0.0004946823,0.9809168,0.0005510841,0.00003366843,0.00009979177,0.00007368843,0.002296362,0.002017565],"genre_scores_gemma":[0.5547828,0.0003877816,0.4327622,0.0008577046,0.0001213667,0.0002491354,0.0006099803,0.0003467878,0.009882308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006412088,"threshold_uncertainty_score":0.03391075,"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."}}