{"id":"W4417138045","doi":"10.1055/a-2668-0824","title":"Core GRADE for evidence syntheses","year":2025,"lang":"de","type":"article","venue":"physioscience","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certainty; Context (archaeology); Strengths and weaknesses; Core (optical fiber); Quality (philosophy); Clinical Practice; Systematic error","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":[0.001121066,0.0003428968,0.0003693391,0.0002215507,0.001114437,0.0006735307,0.002884273,0.0001078509,0.000014647],"category_scores_gemma":[0.003249456,0.000323022,0.000191964,0.001827542,0.0004279757,0.001045844,0.0005833653,0.0002759279,0.0001495781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003373,"about_ca_system_score_gemma":0.0008240287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001199848,"about_ca_topic_score_gemma":0.000004472329,"domain_scores_codex":[0.9968047,0.0001071763,0.0004108115,0.001230329,0.0005455649,0.0009014035],"domain_scores_gemma":[0.9932974,0.004984024,0.00022526,0.00107462,0.000240628,0.0001780608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002276673,0.0009956176,0.007323482,0.003870249,0.000214626,0.00005783577,0.008666324,0.01294493,0.1440114,0.4172967,0.1600385,0.2443527],"study_design_scores_gemma":[0.0002610548,0.0004543483,0.002944079,0.01289536,0.0001351716,0.00000367914,0.0001215853,0.8838258,0.01854842,0.03390898,0.04591086,0.0009906851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005931613,0.02077789,0.9536935,0.009505124,0.007518521,0.001021414,0.00005764571,0.0003624191,0.00113187],"genre_scores_gemma":[0.9669682,0.0003203493,0.02775114,0.001972069,0.0002949234,0.00009022767,0.00000212255,0.00001361832,0.002587297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9610366,"threshold_uncertainty_score":0.9999222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1621154739638729,"score_gpt":0.3562746022338811,"score_spread":0.1941591282700083,"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."}}