{"id":"W4415750076","doi":"10.1021/acs.jpclett.5c02620","title":"Transferable Learning of Reaction Pathways from Geometric Priors","year":2025,"lang":"en","type":"article","venue":"The Journal of Physical Chemistry Letters","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Basic Energy Sciences; National Defense Science and Engineering Graduate; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Massachusetts Institute of Technology","keywords":"Prior probability; Geodesic; Interpolation (computer graphics); Path (computing); Artificial neural network; Scalability; Equivariant map; Orthogonality","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007312465,0.00113251,0.0007587319,0.0005548643,0.0003479744,0.000700999,0.001777409,0.001257632,0.003748717],"category_scores_gemma":[0.003334821,0.0007423027,0.0007857835,0.0004459016,0.0008147353,0.001869471,0.001108985,0.001826718,0.0008139291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009827544,"about_ca_system_score_gemma":0.001387184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002569998,"about_ca_topic_score_gemma":0.003217403,"domain_scores_codex":[0.9997743,0.0000625351,0.000008788665,0.00008693803,0.00004340284,0.00002408206],"domain_scores_gemma":[0.9990976,0.0005363179,0.00009188978,0.0001319027,0.00009373038,0.00004849812],"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":[0.0000580276,0.00003220121,0.0003123765,0.00004434862,0.00001417532,0.00002991643,0.00001314377,0.972923,0.001358477,0.004501324,0.0005656095,0.02014742],"study_design_scores_gemma":[0.00000382088,0.000009210311,0.00002655107,0.000001943084,0.000001071486,0.000002524436,0.000001496375,0.9957854,0.0004606612,0.003614607,0.00009106381,0.000001578288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1207424,0.0003402469,0.8688042,0.0004131548,0.00005952774,0.00009091122,0.0005673543,0.003919726,0.005062636],"genre_scores_gemma":[0.8729475,0.0002024023,0.1222215,0.0001518371,0.00003876914,0.0002076426,0.00130375,0.0003857106,0.002540775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003748717,"threshold_uncertainty_score":0.0125407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00668413428431352,"score_gpt":0.2293044915976815,"score_spread":0.222620357313368,"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."}}