{"id":"W4408181626","doi":"10.22541/essoar.174129298.81850235/v1","title":"Defining an independent reference model for event detection skill scores","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Nuclear Safety and Security Commission; Alberta Machine Intelligence Institute; National Aeronautics and Space Administration; University of Alberta; National Science Foundation","keywords":"Event (particle physics); Computer science; Psychology; Econometrics; Cognitive psychology; Mathematics; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003522389,0.000293904,0.0006129675,0.0007181051,0.0003124276,0.0004421023,0.001464775,0.0004618285,0.0001585681],"category_scores_gemma":[0.001596537,0.0002163699,0.000477626,0.0004229059,0.00004194236,0.0002405321,0.0009750974,0.0005144043,0.00006980937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000124958,"about_ca_system_score_gemma":0.0004356447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007071647,"about_ca_topic_score_gemma":0.01001929,"domain_scores_codex":[0.9956269,0.0002092575,0.001097222,0.001336391,0.001425908,0.0003043172],"domain_scores_gemma":[0.9963688,0.000802828,0.0004754001,0.001422572,0.0007847591,0.0001456126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008283589,0.00006338004,0.0005750124,0.00001563929,0.00006013937,6.463781e-7,0.0005118069,0.6442562,0.00001862322,0.009373695,0.0003688036,0.3446732],"study_design_scores_gemma":[0.0001166034,0.00002943454,0.0009635841,0.00003079316,0.00006547547,4.59175e-7,0.0003076527,0.6757485,0.0003220761,0.3219436,0.0002848262,0.0001869939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02586072,0.0001990197,0.9657971,0.0003342439,0.0004684688,0.0003683057,0.0001632876,0.00008537815,0.006723498],"genre_scores_gemma":[0.9608611,0.000265644,0.02166791,0.0001609784,0.00004801419,0.0001448948,0.00006051866,0.000009904085,0.01678104],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441292,"threshold_uncertainty_score":0.8823308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1426862218944084,"score_gpt":0.4315118414733023,"score_spread":0.288825619578894,"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."}}