{"id":"W4416195477","doi":"10.56975/ijrti.v10i11.207372","title":"Privacy Preserving Machine Learning using Deidentification Techniques for HR and Payroll Data","year":2025,"lang":"en","type":"article","venue":"International Journal for Research Trends and Innovation","topic":"AI and HR Technologies","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Payroll; Information privacy; Feature (linguistics); Key (lock)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002113847,0.00007948835,0.00009310432,0.002571461,0.0006123788,0.001130474,0.00052004,0.00006114355,0.00001182289],"category_scores_gemma":[0.001857855,0.0000698281,0.00001874369,0.0009410651,0.00006318466,0.001769705,0.0006440688,0.0002607355,3.403015e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005077536,"about_ca_system_score_gemma":0.00002854803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009935037,"about_ca_topic_score_gemma":0.00002384018,"domain_scores_codex":[0.9990075,0.00001146448,0.0003083255,0.0002243908,0.0002744201,0.0001739631],"domain_scores_gemma":[0.9980292,0.0001149664,0.0001917467,0.0001371226,0.001521522,0.000005395429],"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":[0.0001851427,0.00004193165,0.01250371,0.0001124594,0.00008724471,9.028336e-7,0.00002300919,0.00000893916,0.008329401,0.1801723,0.01545797,0.7830771],"study_design_scores_gemma":[0.0007761706,0.00003779729,0.005246952,0.0002072042,0.0000252535,0.000008571737,0.0001973235,0.1801571,0.001031299,0.1021925,0.7099929,0.0001269557],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.535814,0.001940906,0.3756988,0.0742524,0.001756952,0.001472828,0.0001369003,0.0004336401,0.008493528],"genre_scores_gemma":[0.9888757,0.000241682,0.007123028,0.0002054562,0.0007624034,0.00004566172,0.0004759115,0.00001613236,0.002254023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7829501,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2782726140440096,"score_gpt":0.4870130919707216,"score_spread":0.208740477926712,"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."}}