{"id":"W4412967876","doi":"10.1101/2025.07.14.25331543","title":"CharMark: A Markov Approach to Linguistic Biomarkers in Dementia","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Dementia; Discriminative model; Character (mathematics); Cognition; Cognitive decline; Psychology; Computer science; Cognitive psychology; Artificial intelligence; Linguistics; Medicine; Disease; Mathematics; Psychiatry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009883752,0.0002905118,0.0003743526,0.0007857261,0.00005418307,0.0002043989,0.001758217,0.0001875467,0.00006595237],"category_scores_gemma":[0.0005571691,0.0002984199,0.0001540434,0.0007158534,0.00002588144,0.00004437472,0.001702651,0.0003712167,0.0001026401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008692691,"about_ca_system_score_gemma":0.0002033815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000854723,"about_ca_topic_score_gemma":0.00001987149,"domain_scores_codex":[0.9976476,0.000222589,0.0004420881,0.0009609915,0.000335697,0.0003910656],"domain_scores_gemma":[0.9985344,0.0001535873,0.0001062239,0.0009386099,0.000101813,0.0001653468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001199338,0.001666547,0.06904505,0.002030191,0.001781976,0.0003776127,0.004745577,0.0001914832,0.0005674179,0.01091538,0.01727143,0.8912874],"study_design_scores_gemma":[0.002988586,0.000118592,0.2414606,0.003866093,0.000486451,0.00005605487,0.0002444242,0.5782983,0.01043793,0.02213128,0.1344485,0.005463216],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03318721,0.0007546209,0.6053695,0.001979393,0.00447325,0.001609212,0.00005283045,0.0005421547,0.3520318],"genre_scores_gemma":[0.4701338,0.0001190858,0.5257065,0.00190251,0.0002114037,0.0006306646,0.00003217475,0.0000282203,0.001235605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8858242,"threshold_uncertainty_score":0.9999468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03359475803611821,"score_gpt":0.2770700496144471,"score_spread":0.2434752915783289,"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."}}