{"id":"W3012083778","doi":"10.48550/arxiv.2003.04972","title":"A Comparative Study of Sequence Classification Models for Privacy Policy Coverage Analysis","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Jargon; GRASP; Privacy policy; Microdata (statistics); Classifier (UML); Information privacy; Data science; Information retrieval; Internet privacy; Data mining; World Wide Web; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000442401,0.0002148818,0.0005750832,0.0004883275,0.0004231216,0.00007877702,0.001312151,0.0002348181,0.00001561072],"category_scores_gemma":[0.0003170278,0.0002653469,0.0002712457,0.001979921,0.0002192502,0.0004918391,0.0008947476,0.0003305329,0.000006113994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005059817,"about_ca_system_score_gemma":0.0006792893,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01495235,"about_ca_topic_score_gemma":0.004060571,"domain_scores_codex":[0.9979172,0.0005007481,0.0002825783,0.0008657175,0.0001807237,0.0002530644],"domain_scores_gemma":[0.9979182,0.0001654319,0.0005656366,0.0008041903,0.0003847623,0.0001617333],"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":[0.0005969476,0.001420012,0.008365276,0.0002093593,0.002407115,0.00001924149,0.09412594,0.3292286,0.0002055193,0.5627735,0.0003506604,0.0002978444],"study_design_scores_gemma":[0.00105809,0.0002642459,0.004139965,0.00002970189,0.001611106,9.138262e-8,0.02063138,0.5987163,0.00004431236,0.3724814,0.0005271942,0.0004962608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6344189,0.00001633495,0.3603203,0.0003922176,0.0001010877,0.001850439,0.0003393025,0.0001030672,0.002458315],"genre_scores_gemma":[0.9991215,0.0001994069,0.0001960338,0.00003091722,0.0001383323,0.00001173972,0.0001530395,0.000009460713,0.0001395821],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3647026,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.322944510737313,"score_gpt":0.3236108289440943,"score_spread":0.0006663182067812579,"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."}}