{"id":"W4396233013","doi":"10.1039/d4dd00023d","title":"Towards equilibrium molecular conformation generation with GFlowNets","year":2024,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; University of Toronto; Canadian Institute for Advanced Research; Vector Institute; McGill University; Université de Montréal","funders":"Institut de Valorisation des Données; Canadian Institute for Advanced Research","keywords":"Sampling (signal processing); Molecular dynamics; Statistical physics; Distribution (mathematics); Boltzmann distribution; Boltzmann constant; Chemistry; Computational chemistry; Thermodynamics; Computer science; Physics; Mathematics; Mathematical analysis","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"],"consensus_categories":[],"category_scores_codex":[0.0002286169,0.0001585398,0.0001285405,0.00007323104,0.00005242086,0.003101896,0.0002226876,0.00004082272,0.0001980111],"category_scores_gemma":[0.00006849252,0.000113046,0.00004154515,0.0001879221,0.0001103005,0.005022979,0.00009840869,0.00006848475,0.0007115536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004854452,"about_ca_system_score_gemma":0.0001311227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002065462,"about_ca_topic_score_gemma":0.000001375403,"domain_scores_codex":[0.9986992,0.00002961451,0.0002220693,0.000340325,0.0004484908,0.0002602624],"domain_scores_gemma":[0.9995931,0.00002180763,0.00005049993,0.000234736,0.00003958685,0.00006030847],"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":[0.0000168562,0.00001493567,0.00004143633,0.00006912069,0.000004901007,0.00004970507,0.000182274,0.008534516,0.9803557,0.007995594,0.0005796447,0.002155287],"study_design_scores_gemma":[0.0002389817,0.0002850775,0.0005399327,0.0001731755,0.00002079311,0.0001686778,0.00007576907,0.1116692,0.8788589,0.001687446,0.00570718,0.0005749738],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9080547,0.0001317994,0.07006379,0.0002144174,0.0008261892,0.0001454179,0.00009331795,0.0002646583,0.02020571],"genre_scores_gemma":[0.9978333,0.000002188377,0.0009413406,0.000132701,0.0001580868,0.00001756522,0.0001386856,0.0000214794,0.0007546175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1031346,"threshold_uncertainty_score":0.997933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009524432100433309,"score_gpt":0.2405831357759257,"score_spread":0.2310587036754924,"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."}}