{"id":"W4396775553","doi":"10.2196/54633","title":"A Reliable and Accessible Caregiving Language Model (CaLM) to Support Tools for Caregivers: Development and Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Disability, Independent Living, and Rehabilitation Research; Administration for Community Living","keywords":"Computer science; Quality (philosophy); Set (abstract data type); Reliability (semiconductor); Family caregivers; Psychology; Medicine; Nursing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004354495,0.001303825,0.0005383719,0.0006552257,0.0002834663,0.0007841872,0.00224849,0.0009572584,0.002523445],"category_scores_gemma":[0.01443207,0.0003772977,0.0006221982,0.0003144161,0.0004445646,0.001811344,0.00145967,0.001470689,0.0007947516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001168415,"about_ca_system_score_gemma":0.001987497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007642991,"about_ca_topic_score_gemma":0.005435167,"domain_scores_codex":[0.998539,0.0007020584,0.0001297292,0.0001969975,0.0003451302,0.00008712608],"domain_scores_gemma":[0.9949788,0.003093197,0.0002089629,0.000387881,0.001022898,0.0003081914],"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":[0.002140387,0.006202422,0.02164224,0.003672881,0.0004467359,0.001411967,0.003186681,0.1264258,0.0188286,0.003422112,0.02275658,0.7898636],"study_design_scores_gemma":[0.001119516,0.005920627,0.01063837,0.0004495146,0.0004292323,0.0006720058,0.001450898,0.936548,0.02135254,0.001490633,0.01978754,0.0001411567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8903831,0.001564577,0.0910154,0.0005899961,0.000191412,0.002973035,0.001775464,0.006384993,0.005122097],"genre_scores_gemma":[0.7811347,0.001113001,0.2048987,0.0003062763,0.00003200705,0.002337549,0.00656914,0.0002799723,0.003328629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007642991,"threshold_uncertainty_score":0.02302903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1869762067679215,"score_gpt":0.4712856175556288,"score_spread":0.2843094107877072,"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."}}