{"id":"W2109010760","doi":"10.1109/ssdbm.2006.6","title":"A Disc-based Approach to Data Summarization and Privacy Preservation","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Automatic summarization; Computer science; Data mining; Heuristic; Constraint (computer-aided design); Set (abstract data type); Cluster analysis; Exploit; Algorithm; Theoretical computer science; Information retrieval; Artificial intelligence; Mathematics","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":[0.0001729923,0.00005535018,0.00004499974,0.00006278457,0.00005208983,0.0003851728,0.0009880011,0.00001206493,0.000003014732],"category_scores_gemma":[0.00001842902,0.00004608411,0.000004560035,0.0003013535,0.000007664968,0.002052023,0.001052436,0.00001863622,0.000008090654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005335983,"about_ca_system_score_gemma":0.000009194292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000160504,"about_ca_topic_score_gemma":0.00001384225,"domain_scores_codex":[0.9993086,0.00001497442,0.00009098386,0.0003380761,0.0001475267,0.00009976944],"domain_scores_gemma":[0.9990782,0.00001364068,0.00002248843,0.0008416662,0.00001700614,0.00002697873],"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":[0.000005793183,0.0003747937,0.009758122,0.00006388106,0.00001048207,0.000001631006,0.00008953991,0.001434096,0.0001969719,0.6939375,0.1847799,0.1093472],"study_design_scores_gemma":[0.0001472153,0.00001025736,0.01358312,0.000002537518,0.0000024272,1.217278e-7,0.000002421684,0.9468091,0.00005985763,0.001451341,0.03785469,0.00007693675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00055259,0.000006257305,0.9808813,0.001648325,0.00003486184,0.0001989869,0.000009127153,0.0001061446,0.01656238],"genre_scores_gemma":[0.1497623,0.000001387979,0.8444806,0.0005667775,0.00007774614,0.00001590776,0.001543214,0.000005746856,0.003546372],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.945375,"threshold_uncertainty_score":0.371423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04332015707856461,"score_gpt":0.2489406957837209,"score_spread":0.2056205387051563,"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."}}