{"id":"W4382344724","doi":"10.1021/acs.est.3c00756","title":"Estimating Indoor Pollutant Loss Using Mass Balances and Unsupervised Clustering to Recognize Decays","year":2023,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Trillium Foundation; Government of Canada; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Computer science; Cluster analysis; Pollutant; Hyperparameter; Environmental science; Data mining; Machine learning; Artificial intelligence","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":[0.0008451841,0.0002159832,0.0002085778,0.0003466827,0.0009330987,0.00006993055,0.0005734186,0.0001163219,0.0001643055],"category_scores_gemma":[0.0001467803,0.0002115848,0.00002824127,0.002002538,0.001849436,0.0003805806,0.001377896,0.0002102785,0.0004010683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004823597,"about_ca_system_score_gemma":0.00001253879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006789906,"about_ca_topic_score_gemma":0.000007743028,"domain_scores_codex":[0.9975579,0.00002781179,0.0002979968,0.0007844251,0.0004973509,0.0008344859],"domain_scores_gemma":[0.9993198,0.0000459335,0.00009510337,0.0003200338,0.000001979514,0.0002171713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008577246,0.00002058633,0.2429536,0.000006468779,0.000003817047,0.00003415159,0.0006853357,0.01355034,0.6136788,0.00001127601,0.000007889209,0.1290392],"study_design_scores_gemma":[0.0008671071,0.0004655846,0.236551,0.0001984445,0.00003132437,0.0003160216,0.005836251,0.6397389,0.1107982,0.002708507,0.001123152,0.001365632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925575,0.00002054415,0.005699648,0.0005966406,0.0003134908,0.0002334565,0.00001279382,0.0003044108,0.0002615356],"genre_scores_gemma":[0.9497514,0.00001157525,0.04999014,0.00007820186,0.000050377,0.00001886579,0.000001059335,0.00002076507,0.00007757288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6261885,"threshold_uncertainty_score":0.8628179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02187237681854775,"score_gpt":0.2672143430359481,"score_spread":0.2453419662174003,"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."}}