{"id":"W4410475038","doi":"10.56553/popets-2025-0110","title":"WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles","year":2025,"lang":"en","type":"article","venue":"Proceedings on Privacy Enhancing Technologies","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; HEC Montréal","funders":"","keywords":"k-nearest neighbors algorithm; Attribution; Computer science; Internet privacy; Authorship attribution; Data mining; Psychology; Artificial intelligence; Social psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009226432,0.001257178,0.001726186,0.002364313,0.001467353,0.004312439,0.00376431,0.00205335,0.002579607],"category_scores_gemma":[0.03742593,0.0006705294,0.001701688,0.002304865,0.002642064,0.01073314,0.006837978,0.004439696,0.001321545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001478893,"about_ca_system_score_gemma":0.002087415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001085991,"about_ca_topic_score_gemma":0.0009674131,"domain_scores_codex":[0.9847365,0.006087853,0.0009874612,0.002615398,0.005041595,0.000531233],"domain_scores_gemma":[0.9838495,0.005729104,0.001668442,0.006328276,0.001940195,0.0004844293],"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":[0.0005596588,0.0003521637,0.006253412,0.0003691898,0.0004436556,0.0003390465,0.0007389166,0.2320296,0.007520952,0.2177735,0.007367669,0.5262523],"study_design_scores_gemma":[0.00002747858,0.0001166985,0.0006170679,0.00004784518,0.00003741527,0.0002591271,0.0001027268,0.8156768,0.005721307,0.1721067,0.005229529,0.00005723806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005856934,0.0001880327,0.9914293,0.000196332,0.00005180995,0.00009838065,0.00007838527,0.0009797375,0.001121123],"genre_scores_gemma":[0.5252213,0.0004535662,0.4684442,0.0004109894,0.0001722696,0.0004953443,0.0005797118,0.0003601255,0.003862571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009226432,"threshold_uncertainty_score":0.04879457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0872743034142247,"score_gpt":0.3182470903028738,"score_spread":0.2309727868886491,"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."}}