{"id":"W1755220452","doi":"10.1007/3-540-44886-1_21","title":"Post-supervised Template Induction for Dynamic Web Sources","year":2003,"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":"Dalhousie University","funders":"","keywords":"Computer science; Row; Exploit; Data mining; Dynamic programming; Machine learning; Information extraction; Artificial intelligence; Supervised learning; Dynamic web page; Unsupervised learning; Pattern recognition (psychology); Web page; Information retrieval; Database; Algorithm; World Wide Web; Artificial neural network","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":[0.002699524,0.001182807,0.001279472,0.004068785,0.0012502,0.001979769,0.004462705,0.001744035,0.007129025],"category_scores_gemma":[0.009724994,0.001072807,0.00185405,0.003686695,0.0008671523,0.005248589,0.00266229,0.002472096,0.006620565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009256279,"about_ca_system_score_gemma":0.002162031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003180818,"about_ca_topic_score_gemma":0.008164774,"domain_scores_codex":[0.9976024,0.000502591,0.0002064824,0.0006960691,0.0007864512,0.0002060775],"domain_scores_gemma":[0.9910098,0.004850185,0.0004381368,0.002200545,0.001289466,0.0002118156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003627201,0.0003134602,0.003335722,0.0003571211,0.0001378342,0.0005471932,0.000209566,0.0301938,0.01459237,0.01324684,0.03117335,0.9055301],"study_design_scores_gemma":[0.00004721978,0.00006820392,0.001002681,0.00005520678,0.0001017647,0.0004462979,0.0001003526,0.9038155,0.0342836,0.04676522,0.0132761,0.00003776865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01010086,0.0003527247,0.9718811,0.0002110401,0.00007923044,0.000142091,0.0016019,0.01406195,0.001569072],"genre_scores_gemma":[0.1672352,0.000520527,0.7983577,0.0001694138,0.0002185814,0.0003243095,0.01834847,0.003077768,0.01174805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007129025,"threshold_uncertainty_score":0.02384895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01669237600718297,"score_gpt":0.2429544541065611,"score_spread":0.2262620780993781,"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."}}