{"id":"W2044979776","doi":"10.1007/s10115-012-0515-8","title":"Anonymizing bag-valued sparse data by semantic similarity-based clustering","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Semantic similarity; Cluster analysis; Information retrieval; Vocabulary; Data publishing; WordNet; Similarity (geometry); Differential privacy; Data mining; Artificial intelligence","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00148499,0.0001759678,0.0002195594,0.0002128116,0.0002123766,0.0005310396,0.00908161,0.0001406789,0.000003714779],"category_scores_gemma":[0.002199099,0.0001632122,0.00002046663,0.000394582,0.00004902357,0.01253638,0.02756143,0.0001800638,0.0002082435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006290734,"about_ca_system_score_gemma":0.00005256409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123969,"about_ca_topic_score_gemma":0.000003973359,"domain_scores_codex":[0.9985305,0.00008153171,0.0005034,0.0002298398,0.0002483749,0.000406331],"domain_scores_gemma":[0.9940308,0.000110819,0.0002108668,0.00543428,0.00009564028,0.0001176297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008851103,0.0001019577,0.003387315,0.00116555,0.0000484839,0.000001143919,0.001341249,0.00007176134,0.0003279968,0.004851207,0.9372299,0.05146454],"study_design_scores_gemma":[0.0002982056,0.00001478621,0.0001550703,0.0001067722,0.00000612469,0.00001467893,0.00008321804,0.7874758,0.0003884126,0.00006062779,0.2112123,0.0001840293],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002658932,0.002375015,0.9843837,0.00105271,0.001430991,0.000386317,0.0001040672,0.0007933152,0.006814944],"genre_scores_gemma":[0.9504251,0.00006534623,0.04869549,0.0002376999,0.0001233604,0.00003080595,0.000369377,0.00001124064,0.00004157914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9477662,"threshold_uncertainty_score":0.9962797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05574438451177503,"score_gpt":0.2877710545662532,"score_spread":0.2320266700544782,"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."}}