{"id":"W4362563893","doi":"10.1039/d3dd00002h","title":"GFlowNets for AI-driven scientific discovery","year":2023,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Machine learning; Data science; Scientific discovery; Artificial intelligence; Leverage (statistics); Pipeline (software); Context (archaeology); Probabilistic logic; Uncertainty quantification; Big data; Data mining","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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007025135,0.0002685356,0.0003041569,0.0002254826,0.0004932005,0.008862437,0.0008736311,0.00007375566,0.0001109021],"category_scores_gemma":[0.0007732653,0.0002238776,0.0001772693,0.0006924624,0.0005037631,0.006749181,0.0004784335,0.00009655484,0.002684219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006187338,"about_ca_system_score_gemma":0.0001702126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001594089,"about_ca_topic_score_gemma":0.00000878676,"domain_scores_codex":[0.9971629,0.00004607169,0.0004064184,0.0009139549,0.0006472636,0.0008234182],"domain_scores_gemma":[0.9987049,0.0002747911,0.00014655,0.0006563443,0.00008900542,0.0001284051],"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":[0.0001044041,0.0001109076,0.003790249,0.0001525613,0.00001024953,0.00002674645,0.0003277076,0.01205585,0.9372378,0.01107197,0.03403336,0.001078205],"study_design_scores_gemma":[0.004029047,0.001225943,0.06620459,0.0007448217,0.0001130205,0.00009302642,0.001093538,0.09406587,0.5166447,0.08609884,0.2246689,0.005017762],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787467,0.0000193246,0.01244358,0.000535902,0.003898453,0.0004604275,0.001260123,0.0005323314,0.002103226],"genre_scores_gemma":[0.9763017,0.000002198248,0.000496424,0.0002068898,0.0002723815,0.0001042054,0.0003844044,0.00004800278,0.02218377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4205931,"threshold_uncertainty_score":0.9980923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01721074264150746,"score_gpt":0.2801339589644358,"score_spread":0.2629232163229284,"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."}}