{"id":"W4404956754","doi":"10.1007/978-3-031-78119-3_18","title":"Primary Key Free Watermarking for Numerical Tabular Datasets in Machine Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada); University of Toronto; McMaster University","funders":"","keywords":"Computer science; Key (lock); Digital watermarking; Artificial intelligence; Machine learning; Data mining; Theoretical computer science; Algorithm; Image (mathematics); Computer security","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":[0.001214472,0.0006469,0.0006851467,0.001417422,0.0002681102,0.0006187877,0.004538217,0.0003452525,0.000004320498],"category_scores_gemma":[0.00008341366,0.0005696141,0.0002020188,0.0007793033,0.0003931248,0.0008460082,0.003226481,0.001525506,0.000007921702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000297721,"about_ca_system_score_gemma":0.0001798784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002690852,"about_ca_topic_score_gemma":0.00004273686,"domain_scores_codex":[0.995725,0.00004461277,0.0006666007,0.001918697,0.0007456242,0.000899491],"domain_scores_gemma":[0.9974841,0.0004948067,0.0002187074,0.00158096,0.00008215451,0.0001393079],"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":[0.00006147069,0.00009378218,0.0006374338,0.0006511663,0.00004662118,0.001073688,0.001650469,0.03176018,0.000641324,0.05863306,0.0001816536,0.9045691],"study_design_scores_gemma":[0.0003275383,0.000222454,0.00004636225,0.001021753,0.00001128403,0.00007075358,8.025513e-8,0.4821908,0.001738907,0.4780695,0.0354403,0.0008602746],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002279738,0.001470626,0.9946848,0.0006498175,0.001084391,0.0006007481,0.00007425017,0.000496625,0.000916001],"genre_scores_gemma":[0.04050774,0.000164465,0.9570603,0.001279772,0.0004018415,0.00006479749,0.000210538,0.00008982139,0.0002207486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9037089,"threshold_uncertainty_score":0.9996755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01254609152788451,"score_gpt":0.2462470019436216,"score_spread":0.2337009104157372,"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."}}