{"id":"W3196408361","doi":"10.33774/chemrxiv-2021-frfhz-v2","title":"Machine Learning of Reaction Properties via Learned Representations of the Condensed Graph of Reaction","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Austrian Science Fund; McGill University","keywords":"Cheminformatics; Computer science; Embedding; Convolutional neural network; Benchmark (surveying); Graph; Artificial intelligence; Molecular graph; Machine learning; Theoretical computer science; Chemistry; Computational chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005102134,0.0009090005,0.0006504501,0.00111909,0.0002240929,0.000860382,0.001312376,0.001010006,0.002481382],"category_scores_gemma":[0.002411284,0.000452116,0.001182257,0.001087194,0.0007231599,0.002130144,0.0006785001,0.001538534,0.0008870364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201404,"about_ca_system_score_gemma":0.0008394995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003339569,"about_ca_topic_score_gemma":0.004820103,"domain_scores_codex":[0.9997701,0.00006015958,0.000009762447,0.00008545387,0.00005287297,0.00002158098],"domain_scores_gemma":[0.9991836,0.0003927493,0.0001338673,0.0001713247,0.0000862504,0.00003221879],"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":[0.00005853717,0.00004634647,0.0008574593,0.0001589212,0.00004363966,0.00004151069,0.00002427176,0.9456936,0.00387542,0.01719242,0.00193699,0.03007076],"study_design_scores_gemma":[0.000004539363,0.000007718345,0.00009975178,0.000005343639,0.000004539078,0.00000617391,0.000002305511,0.9853354,0.001047363,0.01280443,0.0006788475,0.000003727688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08971029,0.0009986002,0.8972151,0.000498966,0.00008766625,0.00008444839,0.003530679,0.003471213,0.004403009],"genre_scores_gemma":[0.7649593,0.001563622,0.2155073,0.0001996513,0.00009717108,0.0002954885,0.0114164,0.0006849315,0.005276109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003339569,"threshold_uncertainty_score":0.008716881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03494659814768778,"score_gpt":0.2872149943753552,"score_spread":0.2522683962276674,"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."}}