{"id":"W4220821430","doi":"10.1016/j.jhazmat.2022.128747","title":"Prediction of heel build-up on activated carbon using machine learning","year":2022,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Ford Motor Company","keywords":"Adsorption; Heel; Activated carbon; Desorption; Chemistry; Chemical engineering; Organic chemistry; Structural engineering; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003838697,0.0001522239,0.0004314411,0.0001023927,0.0001370826,0.00002520981,0.0001984265,0.00007949641,0.002373822],"category_scores_gemma":[0.00008848677,0.0001380609,0.0001663722,0.0001430751,0.0000441736,0.00005647031,0.00007775927,0.000385692,4.959863e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001152672,"about_ca_system_score_gemma":0.00006449909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004219797,"about_ca_topic_score_gemma":1.531627e-7,"domain_scores_codex":[0.9984395,0.00008139639,0.0006813145,0.0001316825,0.0004858314,0.0001802953],"domain_scores_gemma":[0.9987493,0.00005506243,0.0008751054,0.0001470824,0.00009454215,0.00007892778],"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":[0.0006067479,0.0001393879,0.001735712,0.0001446007,0.0001672429,0.00004781813,0.00007779783,0.001586129,0.9953905,0.00001199319,0.00005073586,0.00004135428],"study_design_scores_gemma":[0.0007730413,0.0001950364,0.00007434265,0.0001069248,0.0001271694,0.0003216985,0.0002540204,0.0004466774,0.9965897,0.00008619067,0.0009212859,0.0001039092],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982809,0.00009153903,0.000009833124,0.00003505573,0.0003121903,0.00002402339,0.0001014889,0.00002406944,0.001120879],"genre_scores_gemma":[0.9993668,0.00002112402,0.00006129468,0.00001537988,0.000274999,0.000001663608,0.00001886516,0.00002525879,0.0002146526],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002373326,"threshold_uncertainty_score":0.9985381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02045007894987765,"score_gpt":0.2358890270106283,"score_spread":0.2154389480607506,"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."}}