{"id":"W2823780422","doi":"10.1007/978-3-319-96133-0_10","title":"When Different Is Wrong: Visual Unsupervised Validation for Web Information Extraction","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Outlier; Robustness (evolution); Information extraction; Artificial intelligence; Data mining; Context (archaeology); Information retrieval; Machine learning","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":[0.006149456,0.0009969111,0.0008395859,0.003406543,0.0009917595,0.004169298,0.002422138,0.002201734,0.004718078],"category_scores_gemma":[0.02153685,0.0006198962,0.001019752,0.001443867,0.001614832,0.003418389,0.003738364,0.001924045,0.002607335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007491891,"about_ca_system_score_gemma":0.00150375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004072187,"about_ca_topic_score_gemma":0.007737621,"domain_scores_codex":[0.9964182,0.00107303,0.0002838812,0.0005721683,0.001421936,0.0002307124],"domain_scores_gemma":[0.9853529,0.008954848,0.0008083121,0.002084309,0.002538635,0.0002610197],"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":[0.001014563,0.000189687,0.007251947,0.0008404246,0.0002118752,0.0009385634,0.001646054,0.01455517,0.03325175,0.01895302,0.07794246,0.8432045],"study_design_scores_gemma":[0.0001291089,0.0001242237,0.008615131,0.0008889457,0.0001497996,0.001439514,0.001307948,0.6586561,0.09913882,0.1391048,0.09027478,0.0001709786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0399663,0.001419614,0.9121793,0.001595452,0.0004492897,0.0003332256,0.002219665,0.03320253,0.008634584],"genre_scores_gemma":[0.2672991,0.0006120384,0.7118711,0.001027057,0.000154,0.000249313,0.005697936,0.00600549,0.007083941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006149456,"threshold_uncertainty_score":0.03252184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02195289905482733,"score_gpt":0.2721291305623071,"score_spread":0.2501762315074798,"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."}}