{"id":"W4407723260","doi":"10.31223/x54q65","title":"PoMELO Passive Blind Test Results: Emissions detection and quantification","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Environmental science; Computer science; Geology","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":[0.0003369849,0.0001633682,0.0001442026,0.00005364509,0.0002609823,0.00007460691,0.0001492284,0.0002466656,0.00007277878],"category_scores_gemma":[0.0008479582,0.0001468746,0.00004246283,0.0001527368,0.0001026145,0.00006370075,0.0006696575,0.000397059,0.0000555932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562812,"about_ca_system_score_gemma":0.00001776857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007662008,"about_ca_topic_score_gemma":0.0000898519,"domain_scores_codex":[0.998701,0.0000530232,0.0003329961,0.0005594584,0.0001921465,0.0001614277],"domain_scores_gemma":[0.999047,0.0002944778,0.0001888613,0.0003661075,0.00001536236,0.00008819709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001897743,0.0003474695,0.02446429,0.0002646885,0.00005616068,0.000005631886,0.003076777,0.007307815,0.03911178,0.0001232973,0.005964425,0.9190879],"study_design_scores_gemma":[0.003259488,0.0004345559,0.5568866,0.002141244,0.0003731211,0.00002674935,0.004391641,0.1804856,0.1534065,0.01124013,0.08427534,0.003079047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7041682,0.0001937647,0.08855768,0.007238314,0.003583845,0.002053631,0.0008674969,0.001030051,0.192307],"genre_scores_gemma":[0.9816746,0.0000646913,0.002888887,0.0000303041,0.0001277257,0.00003984895,0.0000494255,0.000008066193,0.01511647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9160088,"threshold_uncertainty_score":0.5989373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04497642479334817,"score_gpt":0.3027213750081725,"score_spread":0.2577449502148244,"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."}}