{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000248946,0.0001322852,0.00009916743,0.0001830848,0.0002035435,0.00006467594,0.00005038054,0.00009999722,0.00008896352],"category_scores_gemma":[0.00005016326,0.0001163516,0.00006674961,0.0003228289,0.00005318869,0.0004656599,0.000003063706,0.0001078781,0.00001446774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005386198,"about_ca_system_score_gemma":0.00002488402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001248665,"about_ca_topic_score_gemma":0.00006570036,"domain_scores_codex":[0.9988886,0.00005607575,0.0002311585,0.0004881967,0.0001813104,0.0001546848],"domain_scores_gemma":[0.9995874,0.0001738442,0.00004241879,0.00009367176,0.00003416757,0.00006852132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000122428,0.00002352693,0.000004414574,0.00003873961,0.000003900957,0.000001816911,0.0004679732,0.0001773851,0.6056798,0.003406043,0.00007830716,0.3899956],"study_design_scores_gemma":[0.0004546503,0.0001957291,0.001818066,0.00003018817,0.00003445601,0.00003402759,0.0002242469,0.4139606,0.5580271,0.0006265716,0.02439518,0.0001991696],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1577408,0.00009234918,0.8339051,0.001875757,0.0006420971,0.0007822004,0.00001571906,0.0005584391,0.004387503],"genre_scores_gemma":[0.9952112,0.00002344953,0.002456921,0.0001254289,0.00008033452,0.0001148312,0.00000748059,0.00002493177,0.001955425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8374704,"threshold_uncertainty_score":0.474468,"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."}}