{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004422683,0.000162946,0.0002498881,0.0003488045,0.0004952951,0.0006960011,0.0005341383,0.0000724657,0.00006875558],"category_scores_gemma":[0.0005085177,0.0001118737,0.0001250622,0.001268781,0.0003762506,0.00174919,0.000234191,0.0001538618,0.00002808331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005417417,"about_ca_system_score_gemma":0.0002756583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000032242,"about_ca_topic_score_gemma":0.000002501387,"domain_scores_codex":[0.9964192,0.00009333914,0.00130195,0.0003563342,0.001622022,0.0002071677],"domain_scores_gemma":[0.9961396,0.00164791,0.0004890032,0.0005315074,0.001113738,0.00007821232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002924297,0.00004750324,0.000009001883,0.00003014106,0.00002153478,4.896144e-7,0.00001798643,0.1611268,0.00008109989,0.8144981,0.0009745824,0.02316349],"study_design_scores_gemma":[0.0002004933,0.0001378511,0.000148593,0.0001859928,0.00006973251,0.0000440333,0.00008527669,0.6855183,0.002352697,0.02670714,0.2843193,0.0002305706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02019006,0.0003943952,0.9479488,0.001804662,0.0002146037,0.0002928406,0.00007984738,0.0001284361,0.02894641],"genre_scores_gemma":[0.8824965,0.00007126045,0.1167596,0.000154927,0.00002829132,0.0000587258,0.0002446144,0.000007130836,0.0001788798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8623065,"threshold_uncertainty_score":0.6711555,"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."}}