{"id":"W2980870580","doi":"10.1038/s41591-019-0624-y","title":"Simpson’s paradox in proof-of-concept studies","year":2019,"lang":"en","type":"letter","venue":"Nature Medicine","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Burden of proof; Proof of concept; Mathematical economics; Epistemology; Mathematics; Philosophy; Computer science; Political science; Law","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":["research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0004307556,0.0003626511,0.001176376,0.000391141,0.00002304801,0.00001162568,0.001613799,0.001351451,0.00001750695],"category_scores_gemma":[0.001006146,0.000228989,0.00008874264,0.0005200398,0.0002946508,0.0001267384,0.0002890968,0.003445093,0.000009545068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008076212,"about_ca_system_score_gemma":0.0001199983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003678184,"about_ca_topic_score_gemma":0.00002251547,"domain_scores_codex":[0.9975169,0.0001207382,0.0005139455,0.0006460899,0.0007726249,0.0004296856],"domain_scores_gemma":[0.9974077,0.001038435,0.0003189681,0.001024148,0.000188076,0.00002268684],"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":[0.000003343763,0.00001158488,0.0001770801,0.0003182544,0.00005996989,0.0004114551,0.001613777,0.000005771969,0.000005130214,0.0004565861,0.9887273,0.008209713],"study_design_scores_gemma":[0.001031711,0.0004073742,0.0005679642,0.001632669,0.00004893482,0.00004393287,0.0002026252,0.0003711076,0.001132702,0.004849392,0.9893143,0.0003973224],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0002886698,0.07459362,0.001986332,0.9165354,0.004400345,0.0005037494,0.000003326112,0.0001056974,0.001582907],"genre_scores_gemma":[0.03616183,0.0003138737,0.00302014,0.9496197,0.005413795,0.00003558274,0.00004227751,0.00003434265,0.005358443],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.07427974,"threshold_uncertainty_score":0.999945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03124954288417557,"score_gpt":0.320930850890397,"score_spread":0.2896813080062214,"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."}}