{"id":"W4317039284","doi":"10.22541/essoar.167397464.40579434/v1","title":"SKB Task Force GWFTS: Pragmatic Validation Using Predictive Modeling Exercises","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Korea Atomic Energy Research Institute; Nuclear Waste Management Organization; U.S. Department of Energy","keywords":"Task (project management); Computer science; Task force; Engineering; Systems engineering; Political science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01318724,0.002455267,0.001443398,0.001642124,0.001734342,0.003613679,0.003104225,0.002531211,0.07300988],"category_scores_gemma":[0.06633308,0.001305737,0.002059643,0.001078935,0.001358382,0.005507292,0.005883314,0.004960819,0.03022499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001068478,"about_ca_system_score_gemma":0.003366171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005583035,"about_ca_topic_score_gemma":0.005714563,"domain_scores_codex":[0.9891116,0.007278728,0.0005070917,0.001119519,0.001667703,0.0003152441],"domain_scores_gemma":[0.9624491,0.02588361,0.0004294147,0.006641907,0.004104131,0.0004918897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009908138,0.000738936,0.001302244,0.001768399,0.0003049623,0.0003487638,0.001277244,0.03175747,0.006914829,0.07174338,0.4441784,0.4386745],"study_design_scores_gemma":[0.001037975,0.0002593061,0.001458537,0.0007915184,0.0002351123,0.0002726302,0.0008685233,0.5410591,0.02328585,0.1642203,0.2663071,0.0002041158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0160788,0.0004529346,0.850304,0.003740329,0.001337307,0.001400684,0.0242225,0.04800756,0.05445596],"genre_scores_gemma":[0.1995421,0.0004858035,0.6577372,0.001171225,0.0005157507,0.002980836,0.0792226,0.02085105,0.03749347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07300988,"threshold_uncertainty_score":0.2442424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04410129765653249,"score_gpt":0.318591841068891,"score_spread":0.2744905434123585,"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."}}