{"id":"W6902500837","doi":"10.6084/m9.figshare.c.3811414_d1.v1","title":"Additional file 1: of ACSC Indicator: testing reliability for hypertension","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); MEDLINE; Clinical trial; Key (lock)","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001837709,0.00006412382,0.0001533253,0.00003274574,0.001519719,0.000006829377,0.0001987588,0.0001781194,0.9876378],"category_scores_gemma":[0.1485904,0.00005345848,0.00003904364,0.00002842614,0.00001424932,0.0001494411,0.0001054147,0.0002857526,0.004023562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004627536,"about_ca_system_score_gemma":0.0005284934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001396356,"about_ca_topic_score_gemma":0.000005100802,"domain_scores_codex":[0.9990174,0.00004415533,0.0003950274,0.000118743,0.0001870229,0.0002376327],"domain_scores_gemma":[0.9895954,0.008749895,0.0007328523,0.000358853,0.0004304499,0.0001326188],"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":[0.000009127567,0.000009791705,0.00006378691,0.001096127,0.000001299302,1.80894e-7,0.00005593458,3.232131e-7,7.72002e-7,0.0000046725,0.9938883,0.004869699],"study_design_scores_gemma":[0.0002069714,0.00004181715,0.04935401,0.005956125,0.000001850453,4.367652e-7,0.00004381566,0.001772321,0.000003423961,0.0001283562,0.942438,0.00005289307],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007445631,0.000003378284,0.000001390657,0.0003083138,0.00007202275,0.0004621898,0.9796784,0.00004725416,0.01935258],"genre_scores_gemma":[0.005276792,2.598297e-7,0.003107398,0.0008616712,0.0003813386,0.002603614,0.9869915,0.000009273715,0.0007681402],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9836142,"threshold_uncertainty_score":0.9997802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4995907800792218,"score_gpt":0.4562314007812946,"score_spread":0.04335937929792716,"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."}}