{"id":"W2974099550","doi":"10.1103/physrevb.100.094107","title":"Deep-learning approach to the structure of amorphous silicon","year":2019,"lang":"en","type":"article","venue":"Physical review. B./Physical review. B","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Regroupement Québécois sur les Matériaux de Pointe","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Compute Canada; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Deep learning; Autoencoder; Computer science; Artificial intelligence; Convolutional neural network; Generative grammar; Set (abstract data type); Silicon; Ab initio; Artificial neural network; Atom (system on chip); Machine learning; Materials science; Physics; Quantum mechanics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001352898,0.0005907613,0.001922324,0.00004906509,0.0001945132,0.0001030099,0.002082666,0.0000516284,0.0006808995],"category_scores_gemma":[0.00215679,0.0003570934,0.0005396364,0.001150957,0.0002597327,0.000299903,0.0006746165,0.0007309142,0.003582211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007049831,"about_ca_system_score_gemma":0.00007773966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005314234,"about_ca_topic_score_gemma":0.000002242748,"domain_scores_codex":[0.9944584,0.001228885,0.0008897384,0.001158902,0.001452375,0.0008116948],"domain_scores_gemma":[0.9964898,0.0005857771,0.0007435592,0.001596686,0.0002585392,0.0003256873],"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":[0.00002037681,0.0003006568,0.0002657139,0.007628514,0.0000160915,0.000001351557,0.0002659766,0.004315572,0.9465422,0.03374193,0.001491547,0.005410083],"study_design_scores_gemma":[0.001538488,0.002776437,0.01171551,0.03573309,0.001781353,0.0001213344,0.0001182561,0.2735254,0.4286711,0.03920031,0.1997108,0.005107936],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9759884,0.01214123,0.003958118,0.001615763,0.0004507614,0.002806926,0.00002797669,0.0001620665,0.002848776],"genre_scores_gemma":[0.988717,0.004829304,0.001264082,0.004308148,0.0005789811,0.00008778812,0.00002454568,0.00006899264,0.0001211204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5178711,"threshold_uncertainty_score":0.9998881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01001660064569628,"score_gpt":0.325430041409327,"score_spread":0.3154134407636308,"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."}}