{"id":"W3094536971","doi":"10.1088/2632-2153/abd51e","title":"Atomic permutationally invariant polynomials for fitting molecular force fields","year":2020,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","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":"Engineering and Physical Sciences Research Council; Agence Nationale de la Recherche; Leverhulme Trust","keywords":"Curse of dimensionality; Force field (fiction); Computer science; Invariant (physics); Extrapolation; Set (abstract data type); Body force; Algorithm; Artificial intelligence; Mathematics; Physics; Classical mechanics; Mathematical analysis; Quantum mechanics","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003904016,0.000491011,0.0007272888,0.0007550827,0.001133136,0.0007945911,0.002202765,0.0005255912,0.0001481491],"category_scores_gemma":[0.009219563,0.0004670602,0.00009041358,0.0009530558,0.001672803,0.0002679243,0.003111868,0.001318663,0.00006058608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001444591,"about_ca_system_score_gemma":0.001000667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002059578,"about_ca_topic_score_gemma":0.00001653215,"domain_scores_codex":[0.9955069,0.000174948,0.0006974382,0.001880992,0.0008178678,0.0009218174],"domain_scores_gemma":[0.9976099,0.0003192885,0.0007118069,0.0006351535,0.0005155678,0.0002083116],"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":[0.00002918062,0.00001851905,0.001735122,0.0002118098,0.000009485382,0.00002420023,0.0003940279,0.00893342,0.9661589,0.02064248,0.00007278127,0.001770045],"study_design_scores_gemma":[0.001010777,0.0007027547,0.001045401,0.0002985256,0.0001038763,0.0001702316,0.0002525232,0.5826142,0.3007788,0.1089637,0.002604043,0.00145523],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9303173,0.0004485961,0.04709793,0.01905951,0.0008154754,0.0009085278,0.00006052645,0.0008270297,0.000465053],"genre_scores_gemma":[0.9510919,0.00002389603,0.04746563,0.0008225413,0.000143866,0.000192944,0.0000345246,0.00005089666,0.0001737966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6653801,"threshold_uncertainty_score":0.9997781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01164860506254879,"score_gpt":0.2740698283941819,"score_spread":0.2624212233316331,"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."}}