{"id":"W4231139425","doi":"10.26434/chemrxiv.14696595","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; Autoregressive model; Generative grammar; Protocol (science); Scale (ratio); Sampling (signal processing); Computer science; Black box; Artificial intelligence; Algorithm; Mathematics; Chemistry; Econometrics; Medicine; Cartography; Computer vision; Geography","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":[0.001642191,0.0004482084,0.0005971204,0.0003096071,0.0006400214,0.001171524,0.00159276,0.001567252,0.008678525],"category_scores_gemma":[0.006399371,0.000480054,0.0007085581,0.0002173989,0.002802383,0.002554164,0.002559732,0.002402719,0.0008981092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006730378,"about_ca_system_score_gemma":0.0006924556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001094972,"about_ca_topic_score_gemma":0.001002985,"domain_scores_codex":[0.9995719,0.0002169877,0.00001652755,0.00006474414,0.00009729541,0.00003251199],"domain_scores_gemma":[0.9977832,0.001504354,0.00007724651,0.0004686978,0.00007450627,0.00009202727],"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":[0.0001123405,0.00004757576,0.000327381,0.00005576829,0.0000256987,0.0001548379,0.0001223905,0.3085337,0.006748524,0.6675699,0.001580552,0.01472123],"study_design_scores_gemma":[0.00002219933,0.00003116167,0.00007324771,0.00001221189,0.00000466871,0.00002697926,0.00001108185,0.7603828,0.002587302,0.2356175,0.001219192,0.00001169046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0503981,0.0002572807,0.9267752,0.002619162,0.0001510422,0.00006696645,0.0002008715,0.0007834403,0.01874798],"genre_scores_gemma":[0.8046792,0.000363669,0.1862967,0.0006692623,0.00009084115,0.0002830958,0.0001855434,0.0007688079,0.006662857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008678525,"threshold_uncertainty_score":0.02903259,"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."}}