{"id":"W2174703538","doi":"10.1007/978-3-642-41230-1_37","title":"Automatically Training Form Classifiers","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Web crawler; Domain (mathematical analysis); Machine learning; Training set; Quality (philosophy); Training (meteorology); Data mining; Artificial intelligence; State (computer science); Information retrieval; World Wide Web; Mathematics","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":[0.001032765,0.001931184,0.001652118,0.00240939,0.001270656,0.002849034,0.002014171,0.00169765,0.02137734],"category_scores_gemma":[0.003717565,0.0008408373,0.001476903,0.001890585,0.0006680064,0.004907445,0.002854945,0.002033685,0.02322403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008723073,"about_ca_system_score_gemma":0.0009201752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001416737,"about_ca_topic_score_gemma":0.003215648,"domain_scores_codex":[0.9985566,0.0001870972,0.00007718379,0.0005367641,0.0004915175,0.0001509388],"domain_scores_gemma":[0.9987871,0.0003513134,0.0000693122,0.0003261727,0.0004124922,0.00005363924],"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":[0.0001426659,0.00008099598,0.001126706,0.0001034974,0.00002839595,0.0001163159,0.00007097219,0.00383879,0.009697177,0.007004787,0.02903006,0.9487597],"study_design_scores_gemma":[0.00007089021,0.0002400656,0.002565544,0.000223713,0.000173545,0.001448507,0.0003637255,0.6943678,0.08685347,0.07275118,0.1408877,0.00005371017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02410976,0.001663742,0.9233162,0.0006566629,0.0006138805,0.0003276016,0.001498575,0.02659962,0.02121394],"genre_scores_gemma":[0.1621319,0.001366257,0.7714282,0.0004765061,0.0003896731,0.000348241,0.008162202,0.002309161,0.05338795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02137734,"threshold_uncertainty_score":0.07151425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02991305767942924,"score_gpt":0.2467924122671749,"score_spread":0.2168793545877457,"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."}}