{"id":"W3217363338","doi":"10.22323/1.396.0338","title":"Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse","year":2022,"lang":"en","type":"article","venue":"Proceedings of The 38th International Symposium on Lattice Field Theory — PoS(LATTICE2021)","topic":"Theoretical and Computational Physics","field":"Physics and Astronomy","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Perimeter Institute","funders":"Agencia Estatal de Investigación; Centres de Recerca de Catalunya; Government of Canada; Ministry of Colleges and Universities; Nuclear Physics; Institut Périmètre de physique théorique; Industry Canada; National Science Foundation; Agència de Gestió d'Ajuts Universitaris i de Recerca; Generalitat de Catalunya; Fundación Cellex; U.S. Department of Energy; Office of Science","keywords":"Observable; Computer science; Context (archaeology); Parameter space; Statistical physics; Mode (computer interface); Artificial intelligence; Physics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006788116,0.0001549397,0.0002235464,0.00005587574,0.000135888,0.0000239792,0.001169642,0.00002915751,0.0003674538],"category_scores_gemma":[0.00009287109,0.000107293,0.0001771085,0.0002824441,0.0001591683,0.00012554,0.0003775506,0.000450829,0.000001626655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000274616,"about_ca_system_score_gemma":0.00003481295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001460023,"about_ca_topic_score_gemma":7.809253e-7,"domain_scores_codex":[0.9984506,0.0001186184,0.0004336597,0.0002136854,0.0006186955,0.00016473],"domain_scores_gemma":[0.9979009,0.001272823,0.0004567718,0.0001456171,0.0002000258,0.00002383968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004156849,0.0004192923,0.01139456,0.00004597567,0.0001101047,2.505054e-7,0.001711772,0.011579,0.008551659,0.9651025,0.00003002464,0.0006391564],"study_design_scores_gemma":[0.0008024778,0.000410883,0.002684371,0.0001659355,0.00009727917,0.000003660001,0.003490154,0.08575864,0.01896408,0.8870285,0.0003698254,0.000224244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9534483,0.00003348168,0.0003584046,0.003055795,0.0002787266,0.0003011508,0.000111936,0.000009416935,0.04240279],"genre_scores_gemma":[0.999028,0.000003660726,0.0001081999,0.0002087597,0.00008129199,0.00004404505,0.00001226537,0.00001477161,0.00049895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07807408,"threshold_uncertainty_score":0.4375282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006961524969987348,"score_gpt":0.2351319468905561,"score_spread":0.2281704219205687,"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."}}