{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2774176,0.002559593,0.002438873,0.004495961,0.004889042,0.00509364,0.004482236,0.008973157,0.08114353],"category_scores_gemma":[0.5391253,0.002583666,0.002960891,0.002952941,0.006080568,0.006540739,0.008370846,0.01335289,0.03130735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004946998,"about_ca_system_score_gemma":0.01839956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007479275,"about_ca_topic_score_gemma":0.0008027909,"domain_scores_codex":[0.6929979,0.2243039,0.04779262,0.01022742,0.02056291,0.004115249],"domain_scores_gemma":[0.2882992,0.4415711,0.02346918,0.1539123,0.08762322,0.005125094],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009885306,0.001595416,0.001731466,0.008299116,0.0003333168,0.003358209,0.02281503,0.004421727,0.01323107,0.3260073,0.3103564,0.2979656],"study_design_scores_gemma":[0.004582832,0.002574112,0.002077384,0.006732681,0.0001742382,0.0007734263,0.002222528,0.01021074,0.01289881,0.252327,0.7046161,0.0008100384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007205733,0.000490114,0.6173303,0.01495453,0.00601347,0.3124909,0.008805629,0.004885808,0.02782351],"genre_scores_gemma":[0.02844645,0.0004607574,0.2652656,0.004656766,0.001222675,0.6843972,0.001883105,0.0007034186,0.01296415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7225823,"threshold_uncertainty_score":0.8910727,"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."}}