{"id":"W4415708658","doi":"10.1109/icme59968.2025.11210026","title":"AMUSE: Adaptive Multi-Segment Encoding for Dataset Watermarking","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Digital watermarking; Watermark; Set (abstract data type); Encoding (memory); Embedding; Code (set theory); Image (mathematics); Encoder; Copy protection","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004445503,0.000568194,0.0003442701,0.0008371346,0.0003111232,0.0006813889,0.0007131396,0.0007215429,0.002895957],"category_scores_gemma":[0.002007555,0.0001973011,0.0003576253,0.0006598806,0.0003765212,0.001496044,0.001331641,0.000754489,0.001335101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002650314,"about_ca_system_score_gemma":0.0002884562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002958282,"about_ca_topic_score_gemma":0.0005606846,"domain_scores_codex":[0.9995309,0.00006828003,0.00003278484,0.00007244247,0.0002458706,0.00004975334],"domain_scores_gemma":[0.9991927,0.0001693774,0.0001109114,0.0003243468,0.0001614413,0.00004131662],"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":[0.0007092183,0.0001200367,0.0007875981,0.0002408011,0.00005423445,0.0003026601,0.0002518782,0.01051341,0.4121129,0.01861158,0.01211136,0.5441844],"study_design_scores_gemma":[0.0001025288,0.0004560349,0.001285091,0.00005956079,0.00003980934,0.001091333,0.00008361541,0.369448,0.5514507,0.009897545,0.06597424,0.0001114057],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02421575,0.0004736526,0.9636283,0.0001798877,0.0001581516,0.0001525653,0.0002783231,0.007870261,0.00304308],"genre_scores_gemma":[0.3389135,0.0006982419,0.6459222,0.0002648045,0.0001437769,0.0002981878,0.001438853,0.0009763616,0.01134394],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002895957,"threshold_uncertainty_score":0.009687901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04804217762527513,"score_gpt":0.3209632242562327,"score_spread":0.2729210466309576,"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."}}