{"id":"W3171571526","doi":"10.26434/chemrxiv.14696595.v1","title":"Inside the Black Box: A Physical Basis for the Effectiveness of Deep Generative Models of Amorphous Materials","year":2021,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Amorphous solid; Generative grammar; Computer science; Protocol (science); Autoregressive model; Scale (ratio); Sampling (signal processing); Artificial intelligence; Mathematics; Econometrics; Medicine; Chemistry; Cartography; Geography; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930565,0.000444741,0.0006395083,0.0003370563,0.0006731173,0.001158506,0.001693586,0.001454508,0.005533771],"category_scores_gemma":[0.005813168,0.0004866695,0.0007101091,0.0002117361,0.002845905,0.00241341,0.002739331,0.002165547,0.0005912596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006610539,"about_ca_system_score_gemma":0.0007041569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001004907,"about_ca_topic_score_gemma":0.0009089204,"domain_scores_codex":[0.9994881,0.0002664003,0.00001811789,0.00006448996,0.0001233069,0.00003952676],"domain_scores_gemma":[0.9978449,0.001496986,0.00008527892,0.0004152579,0.00007038064,0.00008707574],"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":[0.0000971663,0.00004926088,0.0003003773,0.00005105992,0.00002610566,0.0001280189,0.000120474,0.4322971,0.006963238,0.5492809,0.0008336567,0.009852642],"study_design_scores_gemma":[0.00002066698,0.00002714461,0.00005591591,0.000009707502,0.000004143207,0.0000184174,0.000009375049,0.8246281,0.002374986,0.1720376,0.0008033187,0.00001053526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07236739,0.0002326524,0.9109245,0.001885132,0.0001051441,0.00006961291,0.0001410273,0.0006634682,0.01361111],"genre_scores_gemma":[0.8368556,0.0003364374,0.1571001,0.0004277161,0.00006398922,0.0002668922,0.0001241403,0.0005246968,0.004300428],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005533771,"threshold_uncertainty_score":0.01851237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0241197385242391,"score_gpt":0.2843745611565126,"score_spread":0.2602548226322735,"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."}}