{"id":"W4399900412","doi":"10.18280/ria.380312","title":"Building a Corpus for the Underexplored Moroccan Dialect (CFMD) Through Audio Segmentations","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Language, Linguistics, Cultural Analysis","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Linguistics; Computer science; Natural language processing; Speech recognition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001994154,0.0001832956,0.0001905503,0.00006291537,0.0007766266,0.0006392156,0.0003046014,0.00003470016,0.001327325],"category_scores_gemma":[0.0002558623,0.0001192673,0.000264402,0.0001593223,0.0002411821,0.0002343024,0.00005138199,0.000151312,0.0003285215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008771895,"about_ca_system_score_gemma":0.00003843763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006895816,"about_ca_topic_score_gemma":0.0008549163,"domain_scores_codex":[0.9987719,0.00003079385,0.0003856317,0.0003528299,0.0001469264,0.0003118975],"domain_scores_gemma":[0.9987153,0.0007063565,0.00007363947,0.0003022552,0.0001578159,0.00004463723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009801151,0.00003564808,0.000002684022,0.0001054781,0.0001951323,0.00001034043,0.05634557,0.00895266,0.001046306,0.9158899,0.005879362,0.01152707],"study_design_scores_gemma":[0.00004539941,0.0001059827,0.000001275914,0.0002173581,0.0004552468,0.00001025367,0.0362003,0.3055522,0.01840792,0.1648757,0.4737175,0.0004108856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01665296,0.01403655,0.9270285,0.01043331,0.007350624,0.001784557,0.0003712774,0.0008505741,0.02149164],"genre_scores_gemma":[0.9752756,0.0002449351,0.00140511,0.0004434412,0.002510934,0.0001803718,0.00004315108,0.00003871812,0.01985777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9586226,"threshold_uncertainty_score":0.9995856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1090863902592334,"score_gpt":0.317473105228068,"score_spread":0.2083867149688347,"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."}}