{"id":"W4392462664","doi":"10.26434/chemrxiv-2024-vt6z8","title":"From Eyes to Cameras: Computer Vision for High-Throughput Liquid-Liquid Separation","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Innovative Microfluidic and Catalytic Techniques Innovation","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of British Columbia Graduate School; Killam Trusts; University of Toronto; Canada Foundation for Innovation","keywords":"Throughput; Computer vision; Separation (statistics); Computer science; Artificial intelligence; Computer graphics (images); Telecommunications; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006876227,0.0007827724,0.000533038,0.0008084849,0.0003427753,0.001801062,0.001247341,0.001372735,0.006666332],"category_scores_gemma":[0.001540018,0.0005643129,0.0005374003,0.0005413665,0.0006897584,0.001263923,0.001471406,0.001476137,0.002817894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008039427,"about_ca_system_score_gemma":0.0009313581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00237288,"about_ca_topic_score_gemma":0.003264391,"domain_scores_codex":[0.999001,0.0001614653,0.00002708932,0.0003138926,0.0004203737,0.0000762468],"domain_scores_gemma":[0.9994028,0.0002233187,0.00006105818,0.00008808089,0.0001651839,0.00005973148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002725759,0.0002046908,0.001061016,0.0004166501,0.0001144274,0.0001431746,0.0001854356,0.01165933,0.3339494,0.006823422,0.01900188,0.6261681],"study_design_scores_gemma":[0.00009701637,0.0004057812,0.004241858,0.0001341318,0.00008238802,0.000716252,0.0001422691,0.5279365,0.370374,0.0223872,0.0732925,0.000190186],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008125393,0.001081884,0.9811519,0.0003875438,0.0001310289,0.00009854747,0.0002722473,0.004859101,0.003892396],"genre_scores_gemma":[0.143248,0.001499673,0.8464664,0.0007657456,0.0001323373,0.0002448243,0.0005848104,0.0006558067,0.006402369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006666332,"threshold_uncertainty_score":0.02230108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01462195874568164,"score_gpt":0.2973679054608842,"score_spread":0.2827459467152025,"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."}}