{"id":"W4310557772","doi":"10.48550/arxiv.2211.16763","title":"Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Resources Canada; University of Toronto; Government of Ontario; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Automatic differentiation; Differentiable function; Density functional theory; Polarizability; Computer science; Inverse; Computation; Applied mathematics; Conjugate gradient method; Computational chemistry; Mathematical optimization; Chemistry; Physics; Algorithm; Quantum mechanics; Mathematics; Mathematical analysis; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009666817,0.0003026852,0.0003134297,0.0002198984,0.0003146955,0.0002352096,0.0005472407,0.0001357001,0.00155751],"category_scores_gemma":[0.0001385553,0.0003011199,0.00005132943,0.0002820428,0.0002522512,0.000297972,0.000961842,0.0002952647,0.00001307684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002112616,"about_ca_system_score_gemma":0.0001451005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009528603,"about_ca_topic_score_gemma":0.000002441452,"domain_scores_codex":[0.9971222,0.001288103,0.0002043202,0.0009133292,0.0001787238,0.0002933303],"domain_scores_gemma":[0.9985785,0.0002161285,0.0004364707,0.0005907374,0.00007348491,0.0001046901],"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":[0.00007616377,0.00003272188,0.0006839407,0.0001005066,0.00001884194,0.00007606693,0.0002127936,0.9784465,0.01790824,0.002419396,0.00000372079,0.00002115695],"study_design_scores_gemma":[0.0003170802,0.00007512712,0.0003458999,0.00007361814,0.0001738532,0.000009402323,0.00009862995,0.9889439,0.002158595,0.007438266,0.000002107886,0.0003635302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5040285,0.000007662513,0.4953751,0.000006707211,0.0001678793,0.0002725213,0.000006348483,0.0001004428,0.00003483226],"genre_scores_gemma":[0.8855444,0.00001324086,0.1142032,0.00005706265,0.00001472069,0.000003538289,0.00002073989,0.00003252245,0.0001106015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3815159,"threshold_uncertainty_score":0.9999441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04948133002670536,"score_gpt":0.1961714525447733,"score_spread":0.1466901225180679,"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."}}