{"id":"W2162076845","doi":"10.1145/1645953.1646270","title":"Data extraction from the web using wild card queries","year":2009,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Unary operation; Tuple; Information retrieval; Task (project management); Information extraction; Set (abstract data type); Web query classification; Simple (philosophy); Query language; Web search query; Search engine; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001961139,0.0000583607,0.00007184727,0.00002071962,0.000146096,0.000286946,0.001233027,0.00002106157,0.00002102697],"category_scores_gemma":[0.00003849305,0.00003666994,0.00002294055,0.0002093906,0.00001682102,0.001057678,0.0002258722,0.00006859556,0.00002656192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000919236,"about_ca_system_score_gemma":0.00004102478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025775,"about_ca_topic_score_gemma":0.0002262939,"domain_scores_codex":[0.999342,0.00003939204,0.00009739825,0.0002718782,0.000147242,0.0001020539],"domain_scores_gemma":[0.9984658,0.00007447856,0.00003916267,0.001378554,0.00001650721,0.00002546552],"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":[0.0000105477,0.0001582799,0.008814747,0.000002638454,0.0002123733,0.00004397044,0.001440491,0.0009000509,0.04344115,0.02628003,0.2397668,0.6789289],"study_design_scores_gemma":[0.0000923578,0.00001633688,0.007304194,0.00001567491,0.00004469768,0.000009049761,0.0002474109,0.8636207,0.0007319107,0.0008447614,0.1269103,0.0001625981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07807951,0.0002207108,0.9097567,0.008362151,0.0002487406,0.0000353717,0.00009428772,0.0001956546,0.003006901],"genre_scores_gemma":[0.8917879,0.00003156203,0.1064395,0.001216464,0.0002041317,2.455727e-7,0.00008663523,0.000002301936,0.0002312506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8627207,"threshold_uncertainty_score":0.2767026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0866031512683388,"score_gpt":0.3185218247687534,"score_spread":0.2319186735004146,"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."}}