{"id":"W4403050034","doi":"","title":"Evaluating the Hybrid Modelling Competition: A Step Towards Developing Good Modelling Practice","year":2024,"lang":"en","type":"article","venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Energy","keywords":"Competition (biology); Computer science; Good practice; Biochemical engineering; Engineering; Ecology; Biology; Engineering ethics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3853459,0.003242482,0.00406095,0.009495467,0.01155342,0.05593582,0.01412882,0.01284969,0.008229701],"category_scores_gemma":[0.4249827,0.001711002,0.002832633,0.01129609,0.0120877,0.05022319,0.02260689,0.01472881,0.002372764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03558285,"about_ca_system_score_gemma":0.06899525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01929129,"about_ca_topic_score_gemma":0.02462412,"domain_scores_codex":[0.6247922,0.238909,0.02223022,0.01277451,0.09126159,0.01003258],"domain_scores_gemma":[0.4482649,0.262077,0.02761135,0.05289859,0.1864355,0.02271266],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0006414609,0.002497493,0.01949445,0.004916636,0.0007628181,0.0005391951,0.02419558,0.03762914,0.003133647,0.4703602,0.131496,0.3043336],"study_design_scores_gemma":[0.0005252805,0.002331512,0.01012104,0.01486876,0.0003626814,0.0002255586,0.05273831,0.05847613,0.004891777,0.4784979,0.3759966,0.0009644788],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09964509,0.01413133,0.4012677,0.3493155,0.005803033,0.005541139,0.001968533,0.002368512,0.1199591],"genre_scores_gemma":[0.3656736,0.005036043,0.6004539,0.0154093,0.0005437099,0.003881046,0.00208751,0.001146856,0.005768016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6146541,"threshold_uncertainty_score":0.757978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1213137477880347,"score_gpt":0.3844085623189867,"score_spread":0.263094814530952,"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."}}