{"id":"W4408063654","doi":"10.1063/5.0250837","title":"MOLPIPx: An end-to-end differentiable package for permutationally invariant polynomials in Python and Rust","year":2025,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brockhouse Institute for Materials Research; McMaster University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Python (programming language); Invariant (physics); End-to-end principle; Differentiable function; Computation; Artificial neural network; Gaussian; Theoretical computer science; Computational science; Artificial intelligence; Algorithm; Programming language; Mathematics; Physics","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":[0.00151299,0.000122978,0.0002856651,0.00005509664,0.00008088669,0.0001299773,0.0005089445,0.00004401999,0.00009548844],"category_scores_gemma":[0.0004226172,0.00008278618,0.00004012938,0.0001693164,0.0001358058,0.0002643432,0.0001320261,0.0001547445,0.000005094846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005302508,"about_ca_system_score_gemma":0.0001215376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003544986,"about_ca_topic_score_gemma":0.000002988799,"domain_scores_codex":[0.9987568,0.0001672542,0.000418441,0.0001560912,0.0002737454,0.000227665],"domain_scores_gemma":[0.9988618,0.0005090421,0.0002410311,0.0001900498,0.0001102418,0.00008782033],"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":[0.0001730346,0.00006612426,0.0001518273,0.00003262101,0.000004630875,9.552135e-7,0.0004873216,0.0008303018,0.9953846,0.002136595,0.0003092946,0.0004226312],"study_design_scores_gemma":[0.0005638077,0.00009989198,0.003008655,0.00009550747,0.00003528667,0.00001095394,0.00007388619,0.001450013,0.9652057,0.02920648,0.0001324887,0.0001173126],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9824587,0.0000305387,0.01590694,0.001082162,0.0001964755,0.0001634366,0.00001994413,0.000009396082,0.0001324015],"genre_scores_gemma":[0.9917815,0.000004705272,0.007462147,0.0004494261,0.0002217711,0.000005495111,0.000003064005,0.00001083153,0.00006107213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03017895,"threshold_uncertainty_score":0.3375922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01248242346072546,"score_gpt":0.2830535330892795,"score_spread":0.270571109628554,"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."}}