{"id":"W2011364352","doi":"10.1145/1370256.1370278","title":"An enhanced web robot for the CINDI system","year":2008,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Web crawler; Computer science; Digging; Software; Field (mathematics); Robot; Web application; World Wide Web; Artificial intelligence; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001958928,0.00006045659,0.00009064488,0.00003399661,0.0002863126,0.00007959335,0.0009089241,0.00002040102,0.000007789361],"category_scores_gemma":[0.00001132344,0.0000347844,0.00005613572,0.0002073326,0.00001996918,0.0002438677,0.00005664654,0.00003186786,0.00005114116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001114969,"about_ca_system_score_gemma":0.0000431259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004465246,"about_ca_topic_score_gemma":0.00002357926,"domain_scores_codex":[0.9993847,0.00002322423,0.0001055206,0.000219451,0.000118873,0.000148242],"domain_scores_gemma":[0.9990922,0.0001015508,0.0000348176,0.0006861806,0.00004031633,0.00004499401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004251879,0.0005729431,0.002601358,0.000173437,0.0007608453,0.00007793375,0.01085316,0.02235479,0.1150844,0.4187045,0.1137447,0.3150295],"study_design_scores_gemma":[0.000192385,0.00006531682,0.000598681,0.000008131213,0.0000147525,0.00001923744,0.0002822014,0.9878495,0.007222898,0.0000182675,0.003611978,0.0001165895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009577457,0.00003116215,0.9875079,0.0003892004,0.0001217543,0.00006628479,0.000003248058,0.0001845765,0.002118418],"genre_scores_gemma":[0.9483764,0.000005789935,0.05003611,0.000150265,0.00008071669,0.00001848777,0.000003383486,0.000003257549,0.001325627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9654948,"threshold_uncertainty_score":0.2202114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620337048057695,"score_gpt":0.2520494850366246,"score_spread":0.2258461145560477,"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."}}