{"id":"W3039489849","doi":"10.48550/arxiv.2007.01973","title":"Detecting Opportunities for Differential Maintenance of Extracted Views","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Extractor; Focus (optics); Context (archaeology); Information extraction; Information retrieval; Range (aeronautics); Data mining","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000178567,0.0002418102,0.0004822157,0.0002009566,0.0001078354,0.00008658047,0.001714138,0.0001554428,0.00001431562],"category_scores_gemma":[0.0001196449,0.0002620253,0.0003627362,0.0003296934,0.00008007019,0.0002473916,0.001409586,0.0003096283,0.000004848647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005002367,"about_ca_system_score_gemma":0.0001461855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005273001,"about_ca_topic_score_gemma":0.00002410692,"domain_scores_codex":[0.9984626,0.00009720791,0.0002847058,0.0008167551,0.00007697795,0.0002617282],"domain_scores_gemma":[0.9981152,0.0001849714,0.000497966,0.0008845711,0.0001857804,0.000131476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005625403,0.001062436,0.007930214,0.005550229,0.003967864,0.002058541,0.005294588,0.08229773,0.01125292,0.6501983,0.01090527,0.2189194],"study_design_scores_gemma":[0.0004026125,0.00006693495,0.0005082689,0.0002567554,0.0002252293,0.000002175853,0.0003806615,0.986577,0.0007338747,0.009285145,0.001131508,0.0004298521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1369146,0.00002554721,0.8619357,0.000138806,0.0002519979,0.0001447962,0.0001038264,0.000124502,0.0003602028],"genre_scores_gemma":[0.9920769,0.0001043198,0.006946946,0.00004702595,0.00007423382,0.00000145842,0.00004755016,0.00001347182,0.00068809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9042792,"threshold_uncertainty_score":0.9999832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2781871814172543,"score_gpt":0.2203496530893775,"score_spread":0.05783752832787689,"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."}}