{"id":"W4295292764","doi":"10.1016/j.gloepi.2022.100085","title":"P-value, compatibility, and S-value","year":2022,"lang":"en","type":"article","venue":"Global Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compatibility (geochemistry); Confidence interval; Overconfidence effect; Statistics; Statistical hypothesis testing; Mathematics; Econometrics; Computer science; Psychology; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.2766068,0.0002309942,0.004474646,0.00009737507,0.0003529111,0.00006802217,0.001596046,0.00006873919,0.01243321],"category_scores_gemma":[0.1490289,0.0001230835,0.001040878,0.0009867427,0.0001925243,0.0000707194,0.0009980551,0.0002139167,0.001269401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009973029,"about_ca_system_score_gemma":0.00005688125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002775046,"about_ca_topic_score_gemma":0.0000372145,"domain_scores_codex":[0.8900272,0.09318426,0.01195313,0.001820945,0.00246265,0.0005518359],"domain_scores_gemma":[0.9693643,0.02157051,0.004626239,0.00385967,0.0002914606,0.0002878606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006665088,0.00002682291,0.5111565,0.00000687836,0.00006297373,0.000003595983,0.00003818083,0.002112731,0.000001648703,0.2934184,0.183283,0.009882515],"study_design_scores_gemma":[0.0001158151,0.00007147281,0.2596838,0.000001505021,0.00005717397,0.00009212804,0.000209601,0.0286307,1.444547e-7,0.3737675,0.3372615,0.0001086879],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8642747,0.008657141,0.02870519,0.02160036,0.00160707,0.001088464,0.0003004392,0.000025042,0.07374161],"genre_scores_gemma":[0.9785559,0.00001991387,0.01049623,0.009198518,0.00006984426,0.00004901973,0.00001566152,0.000004732522,0.001590205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2514727,"threshold_uncertainty_score":0.9995082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7988932864663181,"score_gpt":0.59056778162296,"score_spread":0.2083255048433581,"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."}}