{"id":"W2034607275","doi":"10.1145/1046456.1046459","title":"Learning important models for web page blocks based on layout and content analysis","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Web page; Block (permutation group theory); Information retrieval; Partition (number theory); Page view; Static web page; Data mining; World Wide Web; Web navigation","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":[0.0003536036,0.0002002775,0.0002997896,0.0004805945,0.0003528921,0.0003548443,0.0005988899,0.00006687111,0.00001193282],"category_scores_gemma":[0.0002069578,0.0001754638,0.0002084373,0.0008906577,0.00004138863,0.0007449358,0.0001484178,0.0001644543,0.00001490417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004178306,"about_ca_system_score_gemma":0.00007187721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006150408,"about_ca_topic_score_gemma":0.0000766659,"domain_scores_codex":[0.9983951,0.00005916821,0.0003922141,0.0005910995,0.0002661491,0.0002962322],"domain_scores_gemma":[0.9983237,0.0002316802,0.0001560139,0.001065966,0.0001071866,0.0001154421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003270999,0.0002920232,0.006642864,0.0000169159,0.0008355855,0.00004607904,0.003073836,0.9574893,0.01300381,0.008258896,0.005671036,0.004637022],"study_design_scores_gemma":[0.0008253599,0.0001712054,0.000175635,0.0000185297,0.0003128498,0.000001281562,0.0002350106,0.9943652,0.0007692239,0.001617438,0.001228807,0.0002794721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1240727,0.00003243297,0.851975,0.0234238,0.00005197617,0.000171194,0.00003146431,0.0001541,0.00008732],"genre_scores_gemma":[0.9279734,0.000009580306,0.06680482,0.004679256,0.00007397772,0.0001224311,0.0001640408,0.00001373546,0.0001587926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8039007,"threshold_uncertainty_score":0.7155205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07156513468895788,"score_gpt":0.263723749372729,"score_spread":0.1921586146837712,"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."}}