{"id":"W6979265938","doi":"","title":"Multilingual MFA: Forced Alignment on Low-Resource Related Languages","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Baseline (sea); Training set; Training (meteorology); Data modeling; Machine translation","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":[0.002189347,0.001952675,0.0008673369,0.0009758259,0.001177999,0.001154784,0.001767096,0.001191639,0.01307765],"category_scores_gemma":[0.006414835,0.0005042049,0.0009249538,0.0009072938,0.0005563261,0.0023968,0.002965614,0.002295982,0.006521887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006438101,"about_ca_system_score_gemma":0.001610487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03040267,"about_ca_topic_score_gemma":0.06052028,"domain_scores_codex":[0.9986992,0.0002596614,0.00007156403,0.0006542152,0.0001517875,0.0001636212],"domain_scores_gemma":[0.9976819,0.0008156457,0.00008671299,0.0007231981,0.0005119788,0.0001805245],"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":[0.002018497,0.0009007507,0.01416728,0.0006506775,0.0006349972,0.0004948507,0.001344227,0.04242108,0.1240353,0.001454701,0.02221178,0.7896658],"study_design_scores_gemma":[0.0006819808,0.00395699,0.08482638,0.0002700872,0.0008777487,0.002050082,0.002405528,0.6389746,0.2072577,0.009160349,0.04899466,0.000543911],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7154849,0.002542869,0.2011322,0.0005986197,0.0009666638,0.0004939369,0.008782176,0.04787459,0.02212397],"genre_scores_gemma":[0.8127725,0.000357105,0.148619,0.0005748041,0.0001169774,0.0003786099,0.02175474,0.004191649,0.01123469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03040267,"threshold_uncertainty_score":0.06045139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03113061162032946,"score_gpt":0.3737070555956762,"score_spread":0.3425764439753468,"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."}}