{"id":"W1512943107","doi":"10.1007/11546849_25","title":"A Machine Learning Approach to Identifying Database Sessions Using Unlabeled Data","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Session (web analytics); Database design; Data mining; Artificial intelligence; Machine learning; Database; World Wide Web","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01042414,0.000515,0.0007136028,0.001809216,0.0007474361,0.001890935,0.009543776,0.0001858252,0.0001931183],"category_scores_gemma":[0.002808222,0.0004136076,0.00009120272,0.001631904,0.0004804073,0.001841778,0.01452409,0.001129119,0.0002464972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002317313,"about_ca_system_score_gemma":0.0003869041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000166321,"about_ca_topic_score_gemma":0.0003663425,"domain_scores_codex":[0.9913861,0.0002031296,0.001113795,0.003108876,0.003454935,0.0007331342],"domain_scores_gemma":[0.993105,0.001240508,0.0005149227,0.004552375,0.0002564314,0.0003307895],"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":[0.00001484113,0.00008252753,0.00006264113,0.00003926496,0.00001945736,0.0000464167,0.0007484172,0.2184834,0.0001817521,0.005923103,0.0004967313,0.7739014],"study_design_scores_gemma":[0.000221992,0.00003193005,0.00002250401,0.0003557401,0.00002836923,0.00003122746,0.000004254966,0.8939723,0.00004285612,0.01695228,0.08774236,0.0005942215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006435049,0.0004345514,0.9912115,0.0006096633,0.001014166,0.0005379739,0.0002881199,0.00008409402,0.005755635],"genre_scores_gemma":[0.02267808,0.00007092687,0.9683414,0.00351534,0.0008489066,0.000006681961,0.0005612111,0.00006191249,0.003915509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7733072,"threshold_uncertainty_score":0.9998316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3182652434517774,"score_gpt":0.4276292084454128,"score_spread":0.1093639649936354,"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."}}