{"id":"W6912323747","doi":"10.5281/zenodo.16729213","title":"MedTranscripts - A multimodal dataset of Spanish medical videos and time-aligned transcripts","year":2025,"lang":"en","type":"dataset","venue":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Gold standard (test); Medical record; Human interaction","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":[0.001126722,0.002183646,0.000969509,0.003244495,0.000690527,0.001176018,0.001887644,0.001722641,0.02154538],"category_scores_gemma":[0.004466814,0.0002650086,0.001039278,0.002484135,0.0004245983,0.0006367857,0.001818425,0.001029122,0.02782905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001241958,"about_ca_system_score_gemma":0.001760066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01326453,"about_ca_topic_score_gemma":0.02933188,"domain_scores_codex":[0.9988068,0.00032509,0.000146761,0.0003073635,0.0002789211,0.0001349281],"domain_scores_gemma":[0.9982862,0.0004580042,0.0001451208,0.0003317579,0.000561639,0.0002173411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006554837,0.0001899095,0.003357312,0.001915221,0.0001236703,0.0005807214,0.0001775159,0.000865823,0.003027458,0.0005623765,0.9428787,0.04566585],"study_design_scores_gemma":[0.0006443245,0.0002460398,0.04399659,0.0009366819,0.0001455765,0.001965751,0.0008744789,0.004988619,0.005379725,0.001907849,0.9387174,0.000196906],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004522824,0.0006503523,0.001407199,0.0002442318,0.0002345059,0.000194019,0.9879884,0.001895161,0.002863292],"genre_scores_gemma":[0.002574626,0.0001252729,0.001715129,0.00007347218,0.00003814461,0.0002768454,0.993964,0.00007311116,0.001159349],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02154538,"threshold_uncertainty_score":0.0720765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09798634213428678,"score_gpt":0.3750296788847213,"score_spread":0.2770433367504345,"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."}}