{"id":"W2144630894","doi":"10.1007/s10844-005-0861-z","title":"Post-Supervised Template Induction for Information Extraction from Lists and Tables in Dynamic Web Sources","year":2005,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Row; Machine learning; Data mining; Artificial intelligence; Dynamic programming; Supervised learning; Exploit; Information extraction; Unsupervised learning; Row and column spaces; Pattern recognition (psychology); Information retrieval; Algorithm; Database; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.0009427791,0.0001158339,0.00022812,0.0008323589,0.00008769397,0.0006985773,0.000279319,0.00009236149,0.000004923459],"category_scores_gemma":[0.0001392376,0.00009719963,0.00007140775,0.0002836607,0.00001278832,0.01376225,0.00003690795,0.0001525152,0.00003061921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000145111,"about_ca_system_score_gemma":0.00008504539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000211994,"about_ca_topic_score_gemma":0.00004746443,"domain_scores_codex":[0.9981535,0.00005043751,0.001257368,0.00006864487,0.0003326015,0.0001374557],"domain_scores_gemma":[0.9981132,0.0001188012,0.001038505,0.0001551274,0.0005027298,0.00007169748],"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":[0.0002384512,0.0001172228,0.002524606,0.0003252703,0.0002313802,0.000001933815,0.03350601,0.07869623,0.005068081,0.002071384,0.001755961,0.8754635],"study_design_scores_gemma":[0.0006500446,0.0001366026,0.001206352,0.0002471331,0.00002371323,0.000126083,0.006966658,0.9118142,0.001128799,0.00004455399,0.07748058,0.0001752554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5063528,0.0002790114,0.4919731,0.0004651542,0.0005752415,0.0001781046,0.00005771096,0.000024526,0.00009433235],"genre_scores_gemma":[0.9912283,0.000214653,0.008183194,0.0001187493,0.0001172514,0.000008479456,0.0001061252,0.000002997281,0.00002025681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8752882,"threshold_uncertainty_score":0.9977296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01489196065337485,"score_gpt":0.2572530941832417,"score_spread":0.2423611335298668,"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."}}