{"id":"W4225713781","doi":"10.1021/acscentsci.1c01002","title":"Routescore: Punching the Ticket to More Efficient Materials Development","year":2022,"lang":"en","type":"article","venue":"ACS Central Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of Toronto","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canada Research Chairs","keywords":"Computer science; Chemical space; Bottleneck; Flexibility (engineering); Synthetic data; Throughput; A priori and a posteriori; Artificial intelligence; Embedded system; Drug discovery; Bioinformatics","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006508192,0.0002671835,0.0002475831,0.0001540988,0.003861274,0.0009108758,0.003672248,0.00002357123,0.002742194],"category_scores_gemma":[0.0006902036,0.0001853693,0.00003328988,0.001493892,0.0007149329,0.0002923672,0.002768515,0.0002177258,0.0004818031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006133103,"about_ca_system_score_gemma":0.0006743976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002341133,"about_ca_topic_score_gemma":0.000008953144,"domain_scores_codex":[0.9943208,0.0003150803,0.0005272371,0.0009732013,0.002324701,0.001538998],"domain_scores_gemma":[0.9984188,0.0001227185,0.0002242103,0.0007800025,0.00009629737,0.0003579631],"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":[0.0000223172,0.00004978455,0.0004602059,0.000006756983,0.000001068242,0.000009874156,0.005980128,0.06532641,0.9260498,0.001063507,0.0004200838,0.0006100564],"study_design_scores_gemma":[0.0001902352,0.0000964839,0.04645391,0.00002193704,0.000006327336,0.00007285309,0.001091796,0.002179923,0.9350558,0.00008812722,0.01425042,0.000492188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912107,0.00001848655,0.001301302,0.002700224,0.003577309,0.0006218219,0.00002955884,0.0001704908,0.000370112],"genre_scores_gemma":[0.9904761,6.330943e-7,0.007042507,0.001902368,0.000127284,0.0001467775,0.000004607845,0.00001985081,0.0002798802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06314648,"threshold_uncertainty_score":0.9981694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009995670752433485,"score_gpt":0.2535607113131043,"score_spread":0.2435650405606708,"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."}}