{"id":"W2117287993","doi":"10.1109/tkde.2008.94","title":"Detecting Word Substitutions in Text","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Sentence; Word (group theory); Natural language processing; Set (abstract data type); Artificial intelligence; Linguistics","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":[0.0002478878,0.00007416542,0.00008150951,0.0002029129,0.0004095084,0.00003191392,0.0001499505,0.0000553642,0.000077173],"category_scores_gemma":[0.00004557798,0.00007919672,0.0000158373,0.0003976918,0.00005167466,0.0006896861,0.000002178723,0.0001701454,0.00006406764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005130095,"about_ca_system_score_gemma":0.00008660275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001904609,"about_ca_topic_score_gemma":0.001427182,"domain_scores_codex":[0.9994247,0.00001857455,0.000141543,0.0001272052,0.00009271912,0.0001952872],"domain_scores_gemma":[0.9995549,0.0001003839,0.00001461785,0.0002008328,0.00002012211,0.0001091426],"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":[0.00006981655,0.0007746851,0.0004196746,0.0002037227,0.0001045457,0.0000498418,0.2680244,0.06859999,0.001995339,0.005770361,0.00357861,0.650409],"study_design_scores_gemma":[0.004252432,0.0001655809,0.01815633,0.0008042565,0.00009475384,0.0001590716,0.01941351,0.3497768,0.009016208,0.00007786416,0.5958295,0.002253684],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.411019,0.0004802556,0.564066,0.0002060111,0.001100628,0.0002967356,0.00007418366,0.0003317157,0.02242551],"genre_scores_gemma":[0.9985502,0.0004970256,0.0004589167,0.00001733618,0.00005424544,0.000002705215,0.000004082472,0.000005943556,0.0004095752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6481553,"threshold_uncertainty_score":0.3229549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06066739218277305,"score_gpt":0.3128019246240537,"score_spread":0.2521345324412806,"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."}}