{"id":"W4385792153","doi":"10.1007/s11042-023-16457-9","title":"Correction: Robust watermarking using diffusion of logo into auto-encoder feature maps","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Digital watermarking; Feature (linguistics); Logo (programming language); Encoder; Artificial intelligence; Pattern recognition (psychology); Computer vision; Data mining; Information retrieval; Image (mathematics); Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001412978,0.0001270539,0.0001528216,0.0001663274,0.0003226686,0.00008594889,0.0003271809,0.00009557527,0.000001949407],"category_scores_gemma":[0.00001420771,0.0001099535,0.00005479596,0.0006946214,0.00009251675,0.0003504579,0.0002602189,0.0001446454,0.000004288338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000184524,"about_ca_system_score_gemma":0.00001835085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002420705,"about_ca_topic_score_gemma":0.000003992498,"domain_scores_codex":[0.999131,0.00002762074,0.0001869054,0.0003200163,0.0001409806,0.0001935335],"domain_scores_gemma":[0.999262,0.0001295504,0.0001014255,0.0003747575,0.00006726755,0.00006495592],"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":[0.00001128851,0.0001167451,0.006402672,0.0001138551,0.00003095505,0.000007323868,0.002988521,0.001476426,0.07674273,0.003884698,0.004210662,0.9040141],"study_design_scores_gemma":[0.0003697853,0.00004365249,0.01260764,0.0001592054,0.00002285491,0.00002940977,0.0001498673,0.9027501,0.02462701,0.01285877,0.04596011,0.0004215537],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01035685,0.00009316619,0.9877257,0.0003766238,0.0002535295,0.0003664658,0.00001462091,0.0005374568,0.0002756029],"genre_scores_gemma":[0.4953946,0.0003380791,0.5031218,0.0001022583,0.0002104216,0.0003017931,0.0001130573,0.00002323051,0.0003946888],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9035926,"threshold_uncertainty_score":0.4483774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02817314940040143,"score_gpt":0.2700033180786561,"score_spread":0.2418301686782547,"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."}}