{"id":"W4382318094","doi":"10.1109/tse.2023.3288901","title":"NLP-Based Automated Compliance Checking of Data Processing Agreements Against GDPR","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Computer science; Table (database); General Data Protection Regulation; Ambiguity; Software; Glossary; Compliance (psychology); Information retrieval; Software engineering; Database; Data Protection Act 1998; Computer security; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003373022,0.0001445446,0.0001982882,0.0002148098,0.0003858672,0.00006398593,0.0005180663,0.00008417412,0.00003265569],"category_scores_gemma":[0.00006367495,0.0001589994,0.00005694199,0.001001613,0.0000641285,0.0004985509,0.000004157486,0.0001567061,0.00003050671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007342731,"about_ca_system_score_gemma":0.0001331308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001421879,"about_ca_topic_score_gemma":0.0001058707,"domain_scores_codex":[0.9986722,0.00002863711,0.0002566737,0.0002845405,0.0004043088,0.000353565],"domain_scores_gemma":[0.9992507,0.0001625416,0.00008191868,0.0003264279,0.00008775848,0.00009071505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002439721,0.0001361839,0.0006138902,0.0003501969,0.00008995602,0.00001906888,0.001442308,0.8118091,0.001259037,0.00002558094,0.0002363367,0.1839939],"study_design_scores_gemma":[0.0006827332,0.0000210747,0.001979903,0.0005795924,0.00004449857,3.222633e-7,0.000301262,0.9910432,0.002146853,0.00000609834,0.002873193,0.000321252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02630774,0.00006173871,0.9698002,0.0001079716,0.0005331926,0.0002339647,0.0001207164,0.002676582,0.0001579446],"genre_scores_gemma":[0.9925578,0.00002762497,0.007137051,0.00004079459,0.00005736037,0.00002667575,0.00002723232,0.00002949549,0.0000959375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9662501,"threshold_uncertainty_score":0.6483806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09377241932177718,"score_gpt":0.3490663702075247,"score_spread":0.2552939508857475,"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."}}