{"id":"W2972981691","doi":"10.1525/elementa.373","title":"Single-blind inter-comparison of methane detection technologies – results from the Stanford/EDF Mobile Monitoring Challenge","year":2019,"lang":"en","type":"article","venue":"Elementa Science of the Anthropocene","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Software deployment; Emerging technologies; Computer science; Leak; Real-time computing; Engineering; Artificial intelligence","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":[0.0005736242,0.0001623437,0.0002156316,0.00001380836,0.0002136363,0.00002066273,0.001396077,0.00006059262,0.0002322631],"category_scores_gemma":[0.00006653037,0.00009870193,0.00007850954,0.0006176875,0.002504223,0.0003505133,0.001166695,0.0001785954,0.00002620022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000335629,"about_ca_system_score_gemma":0.00001385561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001052049,"about_ca_topic_score_gemma":0.00007232137,"domain_scores_codex":[0.9980014,0.00004025908,0.0004582781,0.0004115517,0.0007603342,0.0003281983],"domain_scores_gemma":[0.9986016,0.00008501689,0.0004494967,0.000819998,0.00001113112,0.00003279596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001767987,0.0003984562,0.2060446,0.000007450371,0.00002479047,2.875014e-7,0.001609231,0.01498845,0.5826355,0.00001239742,0.00002992539,0.1940722],"study_design_scores_gemma":[0.0006904732,0.0005438661,0.02723677,0.00005342352,0.0000231314,8.387748e-7,0.01805672,0.003946474,0.9485513,0.0002575819,0.0004830105,0.0001564165],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968472,0.0001599332,0.0005890286,0.000319597,0.0005859439,0.0004468348,0.00001431427,0.00003051879,0.00100666],"genre_scores_gemma":[0.9966354,0.0001441362,0.003100597,0.000008282524,0.00001716778,0.00001045744,0.000001161153,0.0000105064,0.00007223651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3659158,"threshold_uncertainty_score":0.9226915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02108561556356078,"score_gpt":0.2770771473234946,"score_spread":0.2559915317599338,"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."}}