{"id":"W4408758447","doi":"10.1093/qopen/qoaf004","title":"A protocol for structured robustness reproductions and replicability assessments","year":2025,"lang":"en","type":"article","venue":"Q Open","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Deutsche Forschungsgemeinschaft","keywords":"Robustness (evolution); Protocol (science); Computer science; Medicine; Biology; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.001082394,0.00007232617,0.0001598283,0.00006153361,0.0002576295,0.0005513307,0.001096048,0.00004113362,0.00001735757],"category_scores_gemma":[0.0005729407,0.00005896897,0.00004116427,0.0005437628,0.00005841935,0.000426622,0.00103941,0.00008864488,0.0000011249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003979043,"about_ca_system_score_gemma":0.0002027696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006248264,"about_ca_topic_score_gemma":0.00001826268,"domain_scores_codex":[0.9986973,0.00009894475,0.0001891301,0.0007250671,0.0001306053,0.0001588975],"domain_scores_gemma":[0.99829,0.0001532964,0.00004112839,0.001270859,0.0001965896,0.00004811567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004110576,0.001148537,0.08743192,0.001276102,0.0003383121,0.000003685493,0.0002722439,0.002243789,0.0008331177,0.1648307,0.04197166,0.6992389],"study_design_scores_gemma":[0.005037187,0.0003374514,0.09622686,0.0001775862,0.00004084718,0.00001016456,0.0001037798,0.2872507,0.006611946,0.1985171,0.4050746,0.0006117672],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"protocol","genre_scores_codex":[0.001449401,0.000002675097,0.844165,0.005298495,0.00004683302,0.1475658,0.000004848796,0.0000809066,0.001386021],"genre_scores_gemma":[0.0127827,6.332976e-7,0.2861706,0.0002077952,0.00004297177,0.6944075,0.000005323754,0.000006811338,0.006375576],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6986271,"threshold_uncertainty_score":0.5316494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0868313040377392,"score_gpt":0.4803263243522517,"score_spread":0.3934950203145125,"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."}}