{"id":"W4281388444","doi":"10.26226/m.6275705866d5dcf63a31142f","title":"Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Composite number; Domain (mathematical analysis); Computer science; Force field (fiction); Field (mathematics); Artificial intelligence; Materials science; Algorithm; Mathematics; Mathematical analysis","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":[0.00289614,0.0003701281,0.0005283572,0.00009743655,0.0007490044,0.0003606416,0.001087039,0.0001123241,0.0007311677],"category_scores_gemma":[0.0005296221,0.0002315137,0.0001029293,0.0001111336,0.000211947,0.0001276156,0.002619768,0.0006395464,0.00000230181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004773539,"about_ca_system_score_gemma":0.0001061097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187553,"about_ca_topic_score_gemma":0.000172859,"domain_scores_codex":[0.997095,0.0004812746,0.0005226499,0.0008668381,0.0005254881,0.0005087845],"domain_scores_gemma":[0.9974101,0.0009140772,0.0008202464,0.0006696007,0.0001057621,0.00008022213],"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":[0.0006858671,0.0001758434,0.009954956,0.002497912,0.00007650808,0.00001841095,0.007768986,0.1446879,0.8135302,0.01945105,0.0001454865,0.001006922],"study_design_scores_gemma":[0.004138589,0.00291828,0.008720068,0.0007882093,0.0004306698,0.0001969729,0.004747652,0.7349935,0.2112492,0.01945245,0.009496239,0.002868115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8556028,0.0004050175,0.1411228,0.0006163261,0.0004253091,0.001049034,0.0001645005,0.0001289327,0.0004853085],"genre_scores_gemma":[0.9440551,0.00003787065,0.05453674,0.0002080017,0.00007282092,0.0002665146,0.0000627583,0.00004551151,0.000714661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.602281,"threshold_uncertainty_score":0.9440856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01104877312898182,"score_gpt":0.2611283907223339,"score_spread":0.2500796175933521,"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."}}