{"id":"W6996773961","doi":"","title":"Tartarus:A Benchmarking Platform for Realistic And Practical Inverse Molecular Design","year":2023,"lang":"en","type":"article","venue":"University of Groningen research database (University of Groningen / Centre for Information Technology)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; Cégep de Lévis; University of Toronto","funders":"","keywords":"Benchmark (surveying); Benchmarking; Suite; Set (abstract data type); Field (mathematics)","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":[0.003811332,0.0001692563,0.0003212912,0.001318805,0.0009914542,0.00005194663,0.0007496921,0.0002165243,0.0002235383],"category_scores_gemma":[0.001728154,0.0002200732,0.00007573085,0.0009879516,0.001231042,0.001995181,0.0009617413,0.0002623572,0.00006435678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109992,"about_ca_system_score_gemma":0.0003951482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008232237,"about_ca_topic_score_gemma":0.0002307349,"domain_scores_codex":[0.9978831,0.0001353557,0.0002454569,0.0003907524,0.0006638349,0.0006814943],"domain_scores_gemma":[0.9974759,0.0006383507,0.0004015555,0.0004597222,0.0008660026,0.0001585116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006565635,0.0004090031,0.002946508,0.00454205,0.0004411708,0.0002554506,0.02867361,0.02683155,0.5595458,0.2528168,0.0892445,0.027728],"study_design_scores_gemma":[0.008470395,0.002462287,0.001701248,0.0009476618,0.0004042204,0.00005320148,0.08790955,0.674394,0.05320384,0.005757548,0.163282,0.001413994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6119932,0.00002279997,0.382589,0.001914214,0.0001376077,0.0015307,0.001045557,0.0002948122,0.0004721159],"genre_scores_gemma":[0.3440337,0.0002505839,0.6541763,0.0000255477,0.00003090171,0.000002360638,0.001030301,0.00002787824,0.0004223786],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6475624,"threshold_uncertainty_score":0.8974324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05731104528014077,"score_gpt":0.304857145735837,"score_spread":0.2475461004556962,"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."}}