{"id":"W3162926955","doi":"10.48550/arxiv.2105.03902","title":"Learning Gradient Fields for Molecular Conformation Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Computer science; Langevin dynamics; Molecular dynamics; Translation (biology); Algorithm; Field (mathematics); Statistical physics; Force field (fiction); Artificial intelligence; Physics; Computational chemistry; Chemistry; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0007328007,0.000245091,0.0002912993,0.0001213446,0.000294734,0.0002668691,0.0005420744,0.0002684801,0.0003989055],"category_scores_gemma":[0.0002719021,0.0002854364,0.0001512246,0.0001633138,0.0000873604,0.000314718,0.0005372617,0.0003429061,0.00005918036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001482712,"about_ca_system_score_gemma":0.0001582032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001424124,"about_ca_topic_score_gemma":0.00003301459,"domain_scores_codex":[0.9982234,0.0002682131,0.0002681788,0.0007826029,0.0001243904,0.0003332101],"domain_scores_gemma":[0.9987024,0.00007045663,0.0003723826,0.000488185,0.000266534,0.0001000054],"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":[0.00001671104,0.00001918964,0.0001419255,0.000112436,0.000008624083,0.00002686242,0.0003614652,0.8682755,0.125727,0.005121224,0.00009690326,0.00009221214],"study_design_scores_gemma":[0.0003044982,0.00009360669,0.0001129126,0.00006418799,0.00005883762,0.000004555222,0.0002034614,0.9316065,0.06516019,0.001568592,0.0004493686,0.0003733118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5876536,0.00002203582,0.4106558,0.00004861008,0.0009418562,0.0002482118,0.000009366683,0.0001005524,0.000319976],"genre_scores_gemma":[0.9942921,0.00004170108,0.004504932,0.0001115154,0.0001420197,0.000006288893,0.0002144669,0.00001999925,0.0006669886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4066384,"threshold_uncertainty_score":0.9999598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05483604566554429,"score_gpt":0.20320592723399,"score_spread":0.1483698815684457,"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."}}