{"id":"W7117137110","doi":"10.1021/acs.est.5c11814","title":"Performance Evaluation of Survey Solutions in Detecting and Localizing Source-Level Emissions Using a Single-Blind Controlled Testing Protocol","year":2025,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Fossil Energy and Carbon Management","keywords":"Protocol (science); Equivalence (formal languages); Acceptance testing; Methane; Leak; Leak detection","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":[],"consensus_categories":[],"category_scores_codex":[0.005621036,0.001476048,0.0007216859,0.0005733458,0.0005542738,0.0006045532,0.00131001,0.0009453898,0.001418232],"category_scores_gemma":[0.008518372,0.00046045,0.0006756999,0.000333039,0.0007165718,0.0006651157,0.0009353239,0.0004653117,0.0004175943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006702956,"about_ca_system_score_gemma":0.001258005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002527399,"about_ca_topic_score_gemma":0.00379919,"domain_scores_codex":[0.9951244,0.001566111,0.000542139,0.001003702,0.00145339,0.0003101948],"domain_scores_gemma":[0.9926919,0.001536539,0.001439922,0.0007875874,0.003256288,0.0002877625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.009685368,0.008091371,0.02487011,0.001105969,0.0001850902,0.0001794209,0.001123437,0.006075625,0.8670111,0.0002203647,0.0005881443,0.08086403],"study_design_scores_gemma":[0.000979893,0.1541789,0.06096123,0.0001194447,0.0004867414,0.0003783801,0.0009120238,0.0193081,0.7576022,0.0002441068,0.004608536,0.0002204518],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9444298,0.0002153561,0.04891926,0.00004198225,0.00006150176,0.005033362,0.0002370201,0.00026335,0.0007983279],"genre_scores_gemma":[0.8614451,0.0004106805,0.1265722,0.0001690323,0.00003216548,0.008128652,0.0005544284,0.000063678,0.002624071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005621036,"threshold_uncertainty_score":0.02972722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07394372660793147,"score_gpt":0.2947623639859834,"score_spread":0.2208186373780519,"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."}}