{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005506814,0.0004938692,0.0008270934,0.002169794,0.000828715,0.002352921,0.001669512,0.001266293,0.0008868796],"category_scores_gemma":[0.04797031,0.0006527148,0.0007496475,0.001769582,0.001595224,0.00618946,0.002715483,0.001745531,0.0002369335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009688017,"about_ca_system_score_gemma":0.001316743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109867,"about_ca_topic_score_gemma":0.001849346,"domain_scores_codex":[0.9931834,0.001121727,0.0006482219,0.001745155,0.002850616,0.0004508772],"domain_scores_gemma":[0.9417133,0.03256257,0.00776168,0.01150032,0.005344301,0.001117793],"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":[0.001909803,0.0004324591,0.2069359,0.001197763,0.0003274478,0.003602328,0.005703604,0.04735963,0.1201281,0.148488,0.0066247,0.4572903],"study_design_scores_gemma":[0.00008415314,0.0004673073,0.03715121,0.0002264972,0.0003488068,0.00295158,0.001465769,0.5580105,0.196497,0.1774496,0.02519547,0.0001520669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4271703,0.0008121917,0.5646341,0.0008547276,0.00005988732,0.0002240259,0.0008067606,0.003146904,0.002291125],"genre_scores_gemma":[0.8089946,0.0002023224,0.187502,0.0001568051,0.0000526387,0.0001118073,0.001235787,0.0004922358,0.001251807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005506814,"threshold_uncertainty_score":0.02912319,"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."}}