{"id":"W2044838388","doi":"10.1145/2361354.2361393","title":"Personalized document clustering with dual supervision","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Personalization; Matching (statistics); Feature (linguistics); Ask price; Information retrieval; Document clustering; Data mining; Machine learning; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001403385,0.00006071003,0.00005419278,0.00002278157,0.00008665403,0.0001079831,0.0002323787,0.0000132625,0.00008202283],"category_scores_gemma":[0.000002118663,0.00004109782,0.00001371559,0.0001288526,0.00001624109,0.0006750557,0.0001908248,0.0000356056,0.0001161366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001396986,"about_ca_system_score_gemma":0.00001118049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004066944,"about_ca_topic_score_gemma":0.000003751485,"domain_scores_codex":[0.9994413,0.000009798209,0.00006855456,0.0001422739,0.000148873,0.0001892176],"domain_scores_gemma":[0.9995601,0.00001934156,0.00001591919,0.000296076,0.00001779246,0.00009079943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000010508,0.00028431,0.002189614,0.00001980177,0.00004299646,0.000008331146,0.005404413,0.00003984235,0.00143454,0.4023612,0.007775355,0.5804291],"study_design_scores_gemma":[0.00260685,0.0004117035,0.01997472,0.00008996167,0.00003205773,0.0005400541,0.001318042,0.3877166,0.004913468,0.0008646476,0.5803123,0.001219572],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01783597,0.00005372358,0.9763784,0.0008762252,0.00007028737,0.00006804854,0.000001326471,0.0001255188,0.004590489],"genre_scores_gemma":[0.3419622,0.000006650357,0.6559995,0.0003037053,0.00008243139,0.00002494207,0.000006261806,0.000005096505,0.001609312],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5792095,"threshold_uncertainty_score":0.167592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01932422136775616,"score_gpt":0.2607877174463604,"score_spread":0.2414634960786042,"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."}}