{"id":"W2408771376","doi":"10.15200/winn.146857.76572","title":"Verifiable research: The missing link between replicability and reproducibility","year":2016,"lang":"en","type":"dataset","venue":"The Winnower","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Verifiable secret sharing; Reproducibility; Link (geometry); Computer science; Statistics; Mathematics; Computer network; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"theoretical_or_conceptual","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1837125,0.0002538741,0.0004422591,0.0002297092,0.001712749,0.001842242,0.005778143,0.0001623805,0.0007306164],"category_scores_gemma":[0.08792081,0.000099814,0.0001181271,0.0015704,0.001887145,0.0002037697,0.005539274,0.000930361,0.001050754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008179425,"about_ca_system_score_gemma":0.0001878534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004399922,"about_ca_topic_score_gemma":0.00003973771,"domain_scores_codex":[0.9877703,0.003025603,0.001110714,0.004056568,0.003375807,0.0006610383],"domain_scores_gemma":[0.9405505,0.01513007,0.000510376,0.04274841,0.0008851891,0.0001754467],"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":[0.00001502604,0.00001282286,0.0001794322,0.00001011744,0.00001690361,0.000001241465,0.00006851757,7.121161e-7,0.00000260592,0.00002622637,0.8948819,0.1047845],"study_design_scores_gemma":[0.00007894579,0.00002460759,0.004217679,0.00004512292,0.0000241955,0.000002147549,0.00007912566,0.00001940496,0.00001479451,0.04879328,0.9465622,0.0001384653],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001192661,0.0003257056,0.0001214963,0.09598272,0.002322469,0.0009222872,0.897659,0.00005002492,0.001423619],"genre_scores_gemma":[0.01127454,0.0001999227,0.0003920848,0.002939382,0.01521175,0.00015922,0.8848196,0.00009381281,0.08490973],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.104646,"threshold_uncertainty_score":0.9997271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4399944010878472,"score_gpt":0.490721055699281,"score_spread":0.05072665461143383,"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."}}