{"id":"W2152056009","doi":"10.1145/1526709.1526868","title":"News article extraction with template-independent wrapper","year":2009,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Template; Computer science; Information retrieval; Information extraction; Data mining; 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":[0.0001035186,0.00007097312,0.00007818531,0.00006171882,0.00007694469,0.0001781209,0.0002804079,0.00002510797,0.00008901584],"category_scores_gemma":[0.000004637325,0.00004888446,0.0000291261,0.0002981191,0.000007762582,0.0006711104,0.00002592829,0.00006879724,0.0002046833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001340019,"about_ca_system_score_gemma":0.00002031835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007614919,"about_ca_topic_score_gemma":0.00006160182,"domain_scores_codex":[0.9992638,0.00001722743,0.0001050605,0.0002503106,0.0002001598,0.0001634698],"domain_scores_gemma":[0.9994426,0.00001164631,0.00003421189,0.0004114259,0.00002731278,0.0000727459],"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":[0.00005393908,0.0007947672,0.0522889,0.000005850312,0.0001251229,0.0002559335,0.001283275,0.003042515,0.02807744,0.05138862,0.03730896,0.8253747],"study_design_scores_gemma":[0.003125755,0.001887095,0.4253291,0.00007929298,0.0001374363,0.0006544042,0.001612169,0.4354658,0.07624493,0.005699326,0.04788515,0.001879569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376584,0.00001186692,0.8412452,0.003275933,0.00003987931,0.00003494158,3.568852e-7,0.0002082959,0.01752505],"genre_scores_gemma":[0.9496351,0.000002833279,0.04780186,0.0005881304,0.00003017536,0.000001229935,0.000001467944,0.000002146735,0.001937075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8234951,"threshold_uncertainty_score":0.2630858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01283927497978943,"score_gpt":0.2512661544123126,"score_spread":0.2384268794325232,"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."}}