{"id":"W2169763171","doi":"10.1109/icassp.2011.5946841","title":"cROVER: Improving ROVER using automatic error detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Word error rate; Trim; Word (group theory); Reduction (mathematics); Error detection and correction; Artificial intelligence; Speech recognition; Algorithm; 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":[0.000115088,0.00008851755,0.00008060217,0.00006092673,0.0001403284,0.00009644493,0.0004031461,0.00004182638,0.0001191002],"category_scores_gemma":[0.00001514265,0.00006988254,0.00003535902,0.0001530581,0.0000135514,0.001171667,0.000354952,0.0000667761,0.00005654679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003536154,"about_ca_system_score_gemma":0.00002888606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008026139,"about_ca_topic_score_gemma":0.00001922747,"domain_scores_codex":[0.9992582,0.00002134412,0.0001427558,0.0002477868,0.0001483033,0.0001816239],"domain_scores_gemma":[0.9993808,0.00001529284,0.00006839145,0.000443589,0.00003159581,0.00006031368],"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":[0.00000455482,0.00009442347,0.0002423262,0.00002850084,0.00001319188,0.00001718979,0.000796615,0.00003350163,0.04018349,0.004322873,0.0002169228,0.9540464],"study_design_scores_gemma":[0.0001128865,0.00003718579,0.002456137,0.000009504103,0.000003757246,0.00001933159,0.00001694151,0.9750023,0.02119713,0.0007982677,0.0002303045,0.0001162447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05879055,0.00001689983,0.9382022,0.000007768779,0.0004592364,0.00007418753,5.759582e-7,0.0002795723,0.002169011],"genre_scores_gemma":[0.6407374,4.559157e-7,0.3589928,0.00009587451,0.00003662696,0.000002254254,3.171737e-7,0.000005494308,0.0001287606],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9749688,"threshold_uncertainty_score":0.2849727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04782357021298726,"score_gpt":0.2495010374967477,"score_spread":0.2016774672837605,"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."}}