{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002925744,0.0001050823,0.0001301306,0.000354334,0.0002909709,0.001085636,0.0003629048,0.00003952032,0.000005660896],"category_scores_gemma":[0.00008905793,0.00009038395,0.00001673985,0.0004151493,0.00002347383,0.001917126,0.0007264257,0.0001833078,0.00001183926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002434596,"about_ca_system_score_gemma":0.0004542503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004251709,"about_ca_topic_score_gemma":0.00005373828,"domain_scores_codex":[0.9981172,0.0000769316,0.0002036659,0.0004302393,0.0007902085,0.0003817606],"domain_scores_gemma":[0.9990228,0.0002248043,0.00002018085,0.0002773742,0.0003262235,0.0001286374],"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":[0.00001762307,0.00006342529,0.0001831526,0.0003663658,0.00003733186,0.00001140973,0.4910915,0.001296119,0.0002209252,0.003489491,0.002322471,0.5009002],"study_design_scores_gemma":[0.0004132225,0.0003154047,0.0005930792,0.0001249149,0.000004147417,0.000003817124,0.01872224,0.9769633,0.000733122,0.0008554994,0.001132705,0.0001385879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7497768,0.0002160416,0.246822,0.0003187479,0.00007548615,0.001713147,0.000004567991,0.0000693093,0.001003842],"genre_scores_gemma":[0.9773908,0.000005126842,0.02122507,0.0000209435,0.00002503543,0.0009410442,0.000004573137,0.000009390589,0.0003780184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9756671,"threshold_uncertainty_score":0.9999514,"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."}}