{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009650578,0.0005197393,0.0005613345,0.001142427,0.0004205983,0.0007649822,0.002982025,0.0003455188,0.00001780274],"category_scores_gemma":[0.0001297974,0.0004707531,0.0002308531,0.0006978496,0.0004096705,0.0007810955,0.0006163237,0.0005632144,0.00003527876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002018923,"about_ca_system_score_gemma":0.0004784972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002258157,"about_ca_topic_score_gemma":0.0001052324,"domain_scores_codex":[0.9963346,0.00003909649,0.0005181343,0.001723976,0.0007166339,0.0006675192],"domain_scores_gemma":[0.9974049,0.0003470685,0.0002906703,0.001456634,0.000335579,0.0001651927],"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":[0.000009965486,0.00004584889,0.00004867703,0.00007947472,0.00005765619,0.00003540843,0.0009638479,0.01415214,0.002902654,0.004373478,0.0001227351,0.9772081],"study_design_scores_gemma":[0.0004043077,0.0002589438,0.00003340554,0.0002513163,0.00003479499,0.00008533399,8.891882e-7,0.9560007,0.0008402313,0.03511521,0.006093338,0.0008815452],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009982531,0.000360507,0.9945781,0.001553108,0.001484834,0.0003169045,0.00004361606,0.0001698784,0.0004947906],"genre_scores_gemma":[0.1402353,0.000083263,0.8537959,0.003602754,0.0004708097,0.00003100292,0.00008185674,0.00007538107,0.001623748],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9763266,"threshold_uncertainty_score":0.9997744,"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."}}