{"id":"W3173507260","doi":"10.1039/d1sc01206a","title":"TSNet: predicting transition state structures with tensor field networks and transfer learning","year":2021,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Variety (cybernetics); Field (mathematics); Transition state; Chemical physics; Transition (genetics); Tensor (intrinsic definition); State (computer science); Kinetics; Function (biology); Statistical physics; Chemistry; Catalysis; Computational chemistry; Materials science; Computer science; Physics; Mathematics; Artificial intelligence; Organic chemistry; Quantum mechanics; Pure mathematics; Algorithm","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":[0.000752985,0.0001620551,0.0001896617,0.00003871276,0.0004285308,0.0004043118,0.0003379984,0.00005968215,0.0004272895],"category_scores_gemma":[0.0003942272,0.0001230383,0.00002143867,0.000500401,0.0007813031,0.0004301711,0.00009779802,0.000291974,0.000006201823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003270217,"about_ca_system_score_gemma":0.0001110148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004790387,"about_ca_topic_score_gemma":0.000007423258,"domain_scores_codex":[0.9979243,0.0000793835,0.0002162498,0.0007016138,0.0005449859,0.0005335201],"domain_scores_gemma":[0.9992428,0.0001723271,0.0000467813,0.0002010482,0.0001357007,0.0002012736],"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":[0.00003257239,0.000008919334,0.001741277,0.00002012386,0.00000103455,0.00001681448,0.0006921189,0.02434818,0.9719181,0.00009313203,0.000006134724,0.001121597],"study_design_scores_gemma":[0.000240333,0.00009303286,0.003060411,0.00005568964,0.000007567309,0.000124425,0.0001610959,0.04440033,0.9512906,0.0002738949,0.00007745496,0.0002151858],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9670759,0.00006272734,0.03166515,0.0004047861,0.000161098,0.0000854227,0.000002692749,0.000123345,0.0004188881],"genre_scores_gemma":[0.9939458,0.00001219718,0.005549161,0.0003347035,0.00008669255,0.000006742936,0.00000261057,0.00001114036,0.00005098037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02686988,"threshold_uncertainty_score":0.5017355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004366536601512741,"score_gpt":0.2188208635298601,"score_spread":0.2144543269283473,"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."}}