{"id":"W4387937021","doi":"10.1007/s10514-023-10136-2","title":"Large language models for chemistry robotics","year":2023,"lang":"en","type":"article","venue":"Autonomous Robots","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Artificial Intelligence in Medicine (Canada); University of Waterloo; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robotics; Executable; Robot; Task (project management); Artificial intelligence; Natural language; Workspace; Human–computer interaction; Software engineering; Programming language; Systems 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":[],"consensus_categories":[],"category_scores_codex":[0.0003807522,0.0001513029,0.0001683827,0.00005630732,0.00021591,0.0001255167,0.0006648402,0.0001033017,0.00001056728],"category_scores_gemma":[0.00003731923,0.0001559605,0.00008742537,0.0003336757,0.00001329695,0.0002545313,0.0002069516,0.0001310744,0.000137138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004149878,"about_ca_system_score_gemma":0.0001164305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001364604,"about_ca_topic_score_gemma":0.000002791169,"domain_scores_codex":[0.9987287,0.00001810457,0.0001921028,0.0003795117,0.0001423682,0.0005392027],"domain_scores_gemma":[0.9990864,0.0001747578,0.00007272201,0.0005178881,0.00004538183,0.0001028208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003697316,0.00003754207,0.00007118376,0.0000913484,0.00002650789,0.00004798746,0.003320699,0.9562873,0.001381868,0.02092614,0.01139214,0.006413648],"study_design_scores_gemma":[0.0003054758,0.00002352561,0.00003511244,0.00002718762,0.000006445906,0.000008241261,0.00008493609,0.9894836,0.001668052,0.005987175,0.002150505,0.000219753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003280757,0.0002049203,0.9909833,0.001201768,0.0002533904,0.000169761,0.00002444411,0.001136142,0.002745499],"genre_scores_gemma":[0.8311322,0.00001172311,0.1552387,0.0005896582,0.0002351626,0.00008759343,0.0001634821,0.0000492853,0.0124922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8357446,"threshold_uncertainty_score":0.6359885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02230099062276004,"score_gpt":0.2621864641874539,"score_spread":0.2398854735646939,"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."}}