{"id":"W2009759761","doi":"10.1016/j.ins.2012.07.022","title":"Effectiveness of template detection on noise reduction and websites summarization","year":2012,"lang":"en","type":"article","venue":"Information Sciences","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Automatic summarization; Web page; Information retrieval; The Internet; Noise (video); Preprocessor; Template; Data mining; World Wide Web; Artificial intelligence","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":[0.001286835,0.00005002768,0.00006720147,0.0002755986,0.0001771842,0.0001349131,0.0001572546,0.00002505032,0.00000245994],"category_scores_gemma":[0.00009539548,0.0000401059,0.00001625967,0.000690395,0.00007579695,0.005669428,0.00004425182,0.00003040213,0.00002973224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001319917,"about_ca_system_score_gemma":0.00001624414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004377975,"about_ca_topic_score_gemma":6.490231e-7,"domain_scores_codex":[0.9993671,0.00006616309,0.0001593944,0.00007896109,0.0002275127,0.0001009147],"domain_scores_gemma":[0.9995578,0.00009378344,0.0001390177,0.0001127337,0.00006224758,0.00003443769],"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":[0.00006347502,0.0001337365,0.05118897,0.0003193785,0.00004545626,1.282495e-7,0.006953022,0.008566048,0.09441387,0.05279744,0.0001886231,0.7853299],"study_design_scores_gemma":[0.0004340403,0.0003892824,0.3008517,0.0001634592,0.00002161141,0.00003071096,0.0006697988,0.1668907,0.5274549,0.001170548,0.001609808,0.0003135273],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6476661,0.00001715485,0.3503579,0.00004028854,0.0002410036,0.00006169848,0.00000235871,0.00004338225,0.001570173],"genre_scores_gemma":[0.9980693,0.000008774815,0.001879195,0.0000123283,0.00001516072,0.000004072669,0.000004965415,6.526386e-7,0.000005504859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7850163,"threshold_uncertainty_score":0.4110199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0160012018909099,"score_gpt":0.2569754104418357,"score_spread":0.2409742085509258,"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."}}