{"id":"W4205852836","doi":"10.2196/preprints.30474","title":"Using Health Concept Surveying to Elicit Usable Evidence: Case Studies of a Novel Evaluation Methodology (Preprint)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Preprint; USable; Computer science; Incentive; Research design; Vignette; Applied psychology; Psychology; Medical education; Knowledge management; Medicine; World Wide Web; Social psychology; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2265501,0.0009718715,0.0008656362,0.003173784,0.003860355,0.006596158,0.002864536,0.003892343,0.003499816],"category_scores_gemma":[0.2741721,0.0009342488,0.001534079,0.003177979,0.005192495,0.00669346,0.006481667,0.002170058,0.0006465807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006886744,"about_ca_system_score_gemma":0.009093352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001786111,"about_ca_topic_score_gemma":0.003652053,"domain_scores_codex":[0.6682985,0.3107255,0.009588832,0.002054922,0.007425485,0.001906703],"domain_scores_gemma":[0.5395674,0.412788,0.01163106,0.01532939,0.01793357,0.002750699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001753912,0.007592988,0.0385538,0.01828105,0.0006876867,0.009878928,0.3307179,0.006152367,0.006462526,0.06874625,0.01474822,0.4964243],"study_design_scores_gemma":[0.004527255,0.03115377,0.04238997,0.03342217,0.001531509,0.008629546,0.444656,0.04017827,0.03568617,0.06308294,0.2937229,0.001019482],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6439272,0.004424865,0.2491819,0.01731736,0.0006971575,0.04964582,0.0007408103,0.0004144908,0.03365042],"genre_scores_gemma":[0.6243532,0.001999721,0.3452632,0.002153547,0.000094621,0.02338823,0.0001782093,0.00009044398,0.002478853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2265501,"threshold_uncertainty_score":0.9538015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8962973433767693,"score_gpt":0.6859781281098647,"score_spread":0.2103192152669046,"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."}}