{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007126062,0.0004297354,0.0004159967,0.001012242,0.0003264041,0.001184767,0.001891267,0.0002936533,0.00008912788],"category_scores_gemma":[0.00009675764,0.0003770424,0.00017401,0.0003600237,0.0002423404,0.00256999,0.0005792266,0.0003306349,0.000103742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002592057,"about_ca_system_score_gemma":0.0003198379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001449484,"about_ca_topic_score_gemma":0.00001977071,"domain_scores_codex":[0.9970607,0.00002862121,0.0006021112,0.000960686,0.0008841316,0.0004637842],"domain_scores_gemma":[0.9977335,0.0003044087,0.0004063878,0.0009939036,0.0004285564,0.000133202],"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":[0.00001560675,0.00004644148,0.0000686471,0.00007985283,0.00003756909,0.000002745092,0.002610322,0.001628177,0.0007214813,0.002131165,0.001068804,0.9915892],"study_design_scores_gemma":[0.0003871659,0.0002717305,0.0001125931,0.0002099801,0.00003161158,0.00001224096,8.094054e-7,0.9461528,0.006166409,0.03396509,0.01212751,0.0005620742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001227385,0.00004077054,0.9954412,0.0008857553,0.001414602,0.0003615182,0.00003197396,0.0001471233,0.0004496746],"genre_scores_gemma":[0.3502831,0.00006295076,0.6428486,0.003103297,0.002128196,0.00006604767,0.0004723148,0.00005994127,0.0009756292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9910271,"threshold_uncertainty_score":0.9998682,"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."}}