{"id":"W6893545509","doi":"10.5281/zenodo.16729212","title":"MedTranscripts - A multimodal dataset of Spanish medical videos and time-aligned transcripts","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","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":[0.001133444,0.002322013,0.001004244,0.003254463,0.0007066025,0.001165695,0.002006619,0.001816125,0.0202187],"category_scores_gemma":[0.004415025,0.0002749948,0.001081111,0.002464274,0.0004466239,0.0006116993,0.001812226,0.001056541,0.02607854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001261054,"about_ca_system_score_gemma":0.001797239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01364545,"about_ca_topic_score_gemma":0.02946016,"domain_scores_codex":[0.9987675,0.0003296937,0.00014847,0.0003161942,0.0002994815,0.000138767],"domain_scores_gemma":[0.9982948,0.0004524109,0.0001479272,0.0003347191,0.000554573,0.0002156333],"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":[0.0007588096,0.0002132707,0.003476623,0.002052326,0.00014639,0.0006665824,0.0001814952,0.00104941,0.003627588,0.0005675006,0.9384426,0.04881743],"study_design_scores_gemma":[0.0007616584,0.0002945558,0.04730833,0.0009841982,0.0001735487,0.002326661,0.0009015246,0.00608685,0.006387072,0.00196648,0.9325879,0.0002212072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005129277,0.0007343241,0.001637289,0.0002599695,0.0002515065,0.0002290087,0.9866719,0.002118714,0.002967979],"genre_scores_gemma":[0.002879026,0.0001309121,0.001831894,0.00007593945,0.00003983015,0.0002945523,0.9934911,0.0000765136,0.001180126],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0202187,"threshold_uncertainty_score":0.06763828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02059578377920814,"score_gpt":0.274566441788386,"score_spread":0.2539706580091779,"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."}}