{"id":"W4405203783","doi":"10.1145/3658644.3690373","title":"TabularMark: Watermarking Tabular Datasets for Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Precursory Research for Embryonic Science and Technology; Japan Society for the Promotion of Science; Core Research for Evolutional Science and Technology; National Natural Science Foundation of China","keywords":"Digital watermarking; Computer science; Robustness (evolution); USable; Data mining; Artificial intelligence; Machine learning; Watermark; Image (mathematics)","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007920335,0.0001825149,0.0001560939,0.0002020836,0.0001878022,0.0006571237,0.01862463,0.0000922971,0.00006624994],"category_scores_gemma":[0.004743758,0.0001498509,0.00006525834,0.0004176551,0.00004624312,0.001120517,0.06123326,0.0003439887,0.0001070615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005033654,"about_ca_system_score_gemma":0.00003619356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003692763,"about_ca_topic_score_gemma":0.000007528187,"domain_scores_codex":[0.9983084,0.00004315067,0.0002330705,0.0007056763,0.0002386847,0.0004710426],"domain_scores_gemma":[0.9947631,0.0002932984,0.00003384017,0.004826091,0.00002491844,0.00005880099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005681539,0.00002498711,0.0003411681,0.0001814156,0.00007120101,0.0001434832,0.0000448653,0.00003993705,0.003597134,0.02125234,0.7777478,0.19655],"study_design_scores_gemma":[0.0000845346,0.00002493131,0.0000104829,0.00003510261,0.000005627661,0.0000179951,0.000003769711,0.574051,0.008503769,0.03401055,0.383105,0.000147253],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004995664,0.001508527,0.9728398,0.01993176,0.0006787039,0.0002402169,0.000172656,0.003537066,0.000591683],"genre_scores_gemma":[0.1401169,0.0001765023,0.857657,0.0004484084,0.0001083892,0.00008178917,0.0009095769,0.00004153775,0.0004599183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.574011,"threshold_uncertainty_score":0.9866851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02738614540602429,"score_gpt":0.2860790419800042,"score_spread":0.2586928965739799,"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."}}