{"id":"W4406707019","doi":"10.1017/eds.2024.35.pr3","title":"Recommendation: Improving the reproducibility in geoscientific papers: lessons learned from a Hackathon in climate science — R0/PR3","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Engineering and Physical Sciences Research Council; National Oceanic and Atmospheric Administration; Natural Sciences and Engineering Research Council of Canada; McMaster University; Alan Turing Institute; European Commission; Canada Research Chairs; University of Cambridge","keywords":"Reproducibility; Computer science; Data science; Environmental science; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007274883,0.0002935974,0.0003845723,0.0003306006,0.00008374252,0.0002156379,0.000587511,0.0001965243,0.001509574],"category_scores_gemma":[0.001135964,0.0002121975,0.00008439477,0.001976651,0.000174835,0.0001687155,0.0002816333,0.001044086,0.0001457934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005246016,"about_ca_system_score_gemma":0.0002242029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001176027,"about_ca_topic_score_gemma":0.001851231,"domain_scores_codex":[0.9964935,0.00005370774,0.0006299605,0.001907325,0.000384894,0.0005306388],"domain_scores_gemma":[0.9978404,0.0001375698,0.00005194317,0.001819311,0.00005518388,0.00009560977],"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":[0.000003128954,0.00008949562,0.00003071022,0.00977319,0.00001760321,0.000006312028,0.0007750798,0.000344677,0.002278075,0.000125399,0.2464654,0.7400909],"study_design_scores_gemma":[0.00007694359,0.000006999471,0.001375103,0.002115045,0.00003148724,0.000002208308,0.00007950435,0.01816667,0.0001493552,0.0002540017,0.9774117,0.0003309606],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"review","genre_scores_codex":[0.008349449,0.03987318,0.0006225951,0.8348334,0.06654534,0.002400801,0.001225074,0.001795194,0.04435492],"genre_scores_gemma":[0.31752,0.3598473,0.01712009,0.01900837,0.01265908,0.005478108,0.02870187,0.001510969,0.2381542],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8158251,"threshold_uncertainty_score":0.9994032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06532426947686354,"score_gpt":0.3250317109235223,"score_spread":0.2597074414466587,"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."}}