{"id":"W4310183442","doi":"10.18280/isi.270507","title":"A Hybrid Approach for Web Pages Classification","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Web page; Cover (algebra); The Internet; Information retrieval; World Wide Web; Artificial intelligence; Data mining; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000858256,0.0009149292,0.001098635,0.004576811,0.0005233525,0.001336795,0.001394881,0.001548268,0.002358879],"category_scores_gemma":[0.001414947,0.0002952433,0.001298681,0.002596193,0.0003787594,0.001597126,0.000838275,0.0007237996,0.001939475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005641952,"about_ca_system_score_gemma":0.00059051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004178008,"about_ca_topic_score_gemma":0.007504942,"domain_scores_codex":[0.9987161,0.0001917563,0.00009352284,0.0003256408,0.0005495238,0.0001233348],"domain_scores_gemma":[0.999199,0.0001969671,0.00005044644,0.0001207154,0.0003878647,0.00004500951],"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":[0.0003248573,0.0004492862,0.004940197,0.0001856876,0.0003168859,0.0001937268,0.00013963,0.02064076,0.02943333,0.005040395,0.005499918,0.9328353],"study_design_scores_gemma":[0.00002291373,0.0002051537,0.003838723,0.00002846586,0.0001312712,0.0004065345,0.0001150715,0.9686738,0.01098135,0.008134293,0.007413895,0.00004850493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03257808,0.00118546,0.9578744,0.000205249,0.0001516396,0.0002260001,0.0004804802,0.003700295,0.003598401],"genre_scores_gemma":[0.3369975,0.0006109751,0.6446963,0.0002978473,0.0002479272,0.0003550252,0.001823531,0.000235206,0.01473585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004576811,"threshold_uncertainty_score":0.008307397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02966973419881574,"score_gpt":0.2344146807610414,"score_spread":0.2047449465622257,"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."}}