{"id":"W2793111149","doi":"10.1093/bioinformatics/bty153","title":"Data mining of effect sizes from PubMed abstracts: a cross-study conceptual replication","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Université de Toulouse; Agence Nationale de la Recherche","keywords":"Replication (statistics); Computer science; Data mining; Computational biology; Data science; Statistics; Biology; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.01121774,0.0001175013,0.0002548298,0.000162361,0.0001819878,0.0006575963,0.002531773,0.00004185801,0.0001141043],"category_scores_gemma":[0.01444966,0.00008249444,0.00003799036,0.0006174668,0.0003822458,0.000954621,0.001468284,0.00005624925,0.0004327136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001768776,"about_ca_system_score_gemma":0.00003886366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008435193,"about_ca_topic_score_gemma":0.00005146093,"domain_scores_codex":[0.9965344,0.00008985632,0.001325126,0.0005302965,0.001287922,0.0002323885],"domain_scores_gemma":[0.9920413,0.001843453,0.0008084599,0.004934927,0.0002829438,0.00008884714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000947644,0.0002238974,0.1134695,0.00001679509,0.00008188304,0.000001914801,0.01260596,0.00007426947,0.0000366877,0.00006900149,0.1319885,0.7413369],"study_design_scores_gemma":[0.00150297,0.000486744,0.7482431,0.00003783727,0.00006214856,0.000001955598,0.01781248,0.1555706,0.0009187326,0.0002894498,0.07477149,0.0003025608],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859447,0.00001461093,0.005643455,0.00003911287,0.0009867527,0.0004845979,0.0004986419,0.00005718537,0.006330962],"genre_scores_gemma":[0.9870275,5.519593e-7,0.01221311,0.00006368433,0.000142452,0.000008801459,0.0001990361,0.000004477005,0.0003404031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7410343,"threshold_uncertainty_score":0.9938521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2382344275392883,"score_gpt":0.4248347766624087,"score_spread":0.1866003491231205,"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."}}