{"id":"W6912991590","doi":"10.5281/zenodo.7998401","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","year":2024,"lang":"en","type":"preprint","venue":"RWTH Publications (RWTH Aachen)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Canadian Institute for Advanced Research; McGill University; Université de Montréal","funders":"","keywords":"Supervised learning; Training set; Graph; Labeled data; Data point; Range (aeronautics); Data type; Code (set theory)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007823947,0.0006333544,0.000492336,0.0007773443,0.0005147412,0.001141016,0.002988549,0.000474364,0.00002330292],"category_scores_gemma":[0.0003124963,0.0006636364,0.0004154284,0.001194138,0.00009881157,0.0009824577,0.003516288,0.001965794,0.0001616744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002808542,"about_ca_system_score_gemma":0.0006564463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001407036,"about_ca_topic_score_gemma":0.00002232693,"domain_scores_codex":[0.9952432,0.0001901304,0.0007545492,0.002161878,0.0007694418,0.000880794],"domain_scores_gemma":[0.9959143,0.0002881626,0.0004411094,0.00249608,0.0005100819,0.0003502007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000129131,0.0003935498,0.00002579783,0.0001960046,0.0001846199,0.000005863037,0.0004703153,0.3567063,0.00006689616,0.5997694,0.0141785,0.02798994],"study_design_scores_gemma":[0.0003682127,0.00004998568,0.00009373815,0.00009139386,0.00005086868,0.000007121371,0.00001160315,0.7728502,0.00007522774,0.1476528,0.07821312,0.0005356806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003095952,0.0009363652,0.9832764,0.008140351,0.0009972826,0.001564722,0.002054611,0.00120181,0.001518868],"genre_scores_gemma":[0.1497014,0.0001140718,0.8197646,0.00195189,0.0005033981,0.003907863,0.02147825,0.0001990948,0.00237943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4521165,"threshold_uncertainty_score":0.9998959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04311897580672169,"score_gpt":0.3265490492339211,"score_spread":0.2834300734271994,"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."}}