{"id":"W2012940515","doi":"10.1109/compsacw.2010.37","title":"Natural Language Watermarking Based on Syntactic Displacement and Morphological Division","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Morpheme; Computer science; Natural language processing; Agglutinative language; Artificial intelligence; Digital watermarking; Predicate (mathematical logic); Sentence; Linguistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002018574,0.000127397,0.00009849729,0.00009811218,0.0001364542,0.0001218912,0.000345109,0.00005600246,0.00001635535],"category_scores_gemma":[0.00002191049,0.00008134473,0.00004107316,0.0001043205,0.00004915125,0.0002548017,0.0001903859,0.0002831156,0.000003951781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007481175,"about_ca_system_score_gemma":0.000004352653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007276763,"about_ca_topic_score_gemma":0.000003647693,"domain_scores_codex":[0.9991497,0.00003768397,0.0001088354,0.0003168152,0.0001739433,0.0002130386],"domain_scores_gemma":[0.9993966,0.0001124257,0.00003528849,0.0003791542,0.00001383161,0.00006269451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001356315,0.0004565342,0.02910043,0.00006512969,0.00002492608,0.0007171837,0.001062282,0.00005841762,0.5788047,0.05912013,0.0005202238,0.3299344],"study_design_scores_gemma":[0.001344612,0.0008124099,0.07995109,0.0001455537,0.00001412236,0.0001508634,0.00005098003,0.5337298,0.3715498,0.007136567,0.003972587,0.001141621],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6150919,0.00001816046,0.3815016,0.0006207699,0.0003274914,0.0001397596,7.902548e-7,0.0004856477,0.001813911],"genre_scores_gemma":[0.9226088,0.000002067242,0.07667551,0.0006213086,0.00001811626,0.00001024114,0.000002679002,0.000004539525,0.00005676482],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5336714,"threshold_uncertainty_score":0.3317142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006283448400674473,"score_gpt":0.2512344896036514,"score_spread":0.2449510412029769,"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."}}