{"id":"W4415356660","doi":"10.1021/acs.jcim.5c01767","title":"dpdata: A Scalable Python Toolkit for Atomistic Machine Learning Data Sets","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Innovation Studies","funders":"National Key Research and Development Program of China; National Science and Technology Major Project; Xiamen University; Agentúra na Podporu Výskumu a Vývoja; National Natural Science Foundation of China","keywords":"Python (programming language); Scalability; Inference; Software deployment; Data structure; Key (lock); Data point; Data set","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":[],"consensus_categories":[],"category_scores_codex":[0.001920057,0.0000981343,0.0002225632,0.0001106,0.0001240534,0.0003321168,0.0004621567,0.00006022562,0.00004798511],"category_scores_gemma":[0.001744875,0.00007898729,0.00003019713,0.00009737987,0.00004083275,0.001894841,0.0002622787,0.0001920284,0.000007490376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003421449,"about_ca_system_score_gemma":0.0001087142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001838031,"about_ca_topic_score_gemma":3.915293e-7,"domain_scores_codex":[0.9987522,0.00003418695,0.0006927999,0.0001145153,0.0002288366,0.0001774403],"domain_scores_gemma":[0.9990261,0.0001325369,0.000348021,0.0001881312,0.0002292544,0.00007596242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000600729,0.00005083,0.000151862,0.0007602131,0.00002552167,0.000001653916,0.0008475788,0.2962396,0.6814785,0.001841584,0.003332901,0.01466898],"study_design_scores_gemma":[0.0005602562,0.00002539311,0.00000239829,0.0001184119,0.00002393989,0.00002845183,0.00005885528,0.9765455,0.014283,0.0009305031,0.007340937,0.00008242512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4768771,0.0001327206,0.521601,0.0006490621,0.0003080942,0.0001074897,0.00003341015,0.00002844502,0.0002626849],"genre_scores_gemma":[0.9320013,0.00004784546,0.06716118,0.0005771281,0.00008222451,0.000003559625,0.00007622896,0.000005958646,0.00004455498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6803058,"threshold_uncertainty_score":0.3221008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03526463816445469,"score_gpt":0.3185870247305178,"score_spread":0.2833223865660631,"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."}}