{"id":"W2905479309","doi":"10.1039/c8sm02054j","title":"Using machine learning to discover shape descriptors for predicting emulsion stability in a microfluidic channel","year":2018,"lang":"en","type":"article","venue":"Soft Matter","topic":"Innovative Microfluidic and Catalytic Techniques Innovation","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Division of Electrical, Communications and Cyber Systems; Division of Chemical, Bioengineering, Environmental, and Transport Systems","keywords":"Emulsion; Stability (learning theory); Microfluidics; Channel (broadcasting); Artificial intelligence; Computer science; Materials science; Nanotechnology; Machine learning; Engineering; Chemical engineering; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003732353,0.0001840902,0.000180274,0.0002177209,0.0001015722,0.00003518957,0.0001216321,0.00009154375,0.0001683427],"category_scores_gemma":[0.00006240056,0.0001855017,0.00003733971,0.0004824686,0.00005379477,0.0002016385,0.00007690521,0.0001981251,0.00003877662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000246963,"about_ca_system_score_gemma":0.00001215765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009395934,"about_ca_topic_score_gemma":0.000005776763,"domain_scores_codex":[0.9989092,0.00001905657,0.0003594744,0.000259579,0.0001014207,0.0003512081],"domain_scores_gemma":[0.999619,0.00002772601,0.00004024479,0.0001656982,0.0001152836,0.00003202638],"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":[0.00003258599,0.0000164224,0.03436134,0.000100728,0.00001024089,6.05621e-7,0.001465085,0.0000185752,0.9596745,0.00002358864,0.003068164,0.001228097],"study_design_scores_gemma":[0.0003557702,0.0000876574,0.003072844,0.0001509425,0.000009040399,0.000005163456,0.0002151415,0.05422428,0.936608,0.0002879174,0.004681244,0.0003020126],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6193631,0.00009283028,0.3795789,0.00006500614,0.0002089508,0.00034435,0.00002209883,0.0001616747,0.0001631458],"genre_scores_gemma":[0.9964794,0.000001860858,0.002657783,0.0004669321,0.0001817704,0.00005321837,0.00004437989,0.00006065843,0.00005398562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3771164,"threshold_uncertainty_score":0.7564539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03014985998451211,"score_gpt":0.2655752491959775,"score_spread":0.2354253892114654,"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."}}