{"id":"W4402683950","doi":"10.18653/v1/2024.findings-acl.377","title":"OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Translation (biology); Natural language processing; Word (group theory); Artificial intelligence; Speech recognition; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001609297,0.002427399,0.001489417,0.002498937,0.00121758,0.001725839,0.001968954,0.001715847,0.009917644],"category_scores_gemma":[0.006573878,0.0007038675,0.0009350993,0.001932996,0.0008276433,0.002049947,0.002307114,0.001810456,0.00604504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001212288,"about_ca_system_score_gemma":0.003290209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02342012,"about_ca_topic_score_gemma":0.06192803,"domain_scores_codex":[0.9982408,0.000379759,0.0001851999,0.0005821257,0.0004629833,0.0001490765],"domain_scores_gemma":[0.9978612,0.0006423742,0.0002431561,0.0005439157,0.0005911975,0.0001181291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001897704,0.0001791056,0.004031268,0.0008064409,0.0004247797,0.0004475601,0.0003816361,0.0219211,0.05828587,0.004017682,0.05770683,0.8499],"study_design_scores_gemma":[0.0005117206,0.0008309539,0.007410539,0.0001062733,0.0002680461,0.001314155,0.0007307716,0.7678604,0.1437949,0.01583177,0.06099636,0.0003441363],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08508432,0.003391873,0.7557619,0.0005876828,0.000715389,0.0006411367,0.008154348,0.1375894,0.008074015],"genre_scores_gemma":[0.3025636,0.0005157088,0.6624736,0.0003724657,0.0001293768,0.0005135876,0.0153698,0.004784851,0.01327696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02342012,"threshold_uncertainty_score":0.04656762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0524697776650369,"score_gpt":0.2855654338224392,"score_spread":0.2330956561574023,"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."}}