{"id":"W3133194039","doi":"10.1039/d1cc00586c","title":"A graph-convolutional neural network for addressing small-scale reaction prediction","year":2021,"lang":"en","type":"article","venue":"Chemical Communications","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Transformer; Graph; Scale (ratio); Artificial intelligence; Pattern recognition (psychology); Machine learning; Theoretical computer science; Engineering; Physics; Voltage","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":[0.0002884598,0.001093382,0.0004752487,0.0005358775,0.0003428477,0.0004511566,0.001589272,0.00081017,0.002149254],"category_scores_gemma":[0.0008520217,0.0003675493,0.0006286273,0.000904598,0.0003711628,0.001281686,0.0006536302,0.001159479,0.0008152371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070226,"about_ca_system_score_gemma":0.001235221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01618521,"about_ca_topic_score_gemma":0.024853,"domain_scores_codex":[0.9998808,0.00001288824,0.0000050143,0.00004590815,0.00003494827,0.00002045274],"domain_scores_gemma":[0.9997868,0.00007353869,0.00002571394,0.00004199205,0.00005373534,0.00001816028],"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":[0.0001020972,0.0001564068,0.002004299,0.0002274683,0.0001197492,0.0001795583,0.00002945767,0.7720579,0.02715276,0.01956386,0.00839431,0.1700121],"study_design_scores_gemma":[0.000001681825,0.000008619738,0.00008110327,0.000001653027,0.000005853542,0.000009399575,0.000001219713,0.9952395,0.001804363,0.002252043,0.0005911724,0.000003328029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04001807,0.0008778627,0.9478008,0.0003773707,0.0001568087,0.0000918759,0.0008919831,0.005067023,0.004718163],"genre_scores_gemma":[0.5734027,0.001232374,0.4122285,0.0002811606,0.00008194443,0.0001941366,0.003111721,0.0004008122,0.009066645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01618521,"threshold_uncertainty_score":0.03218204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06503386698654104,"score_gpt":0.3124152844991236,"score_spread":0.2473814175125826,"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."}}