{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T06:08:09Z","timestamp":1788761289676,"version":"build-2803163510"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Incomplete judicial records constrain reliable crime analytics because missing attributes, heterogeneous case descriptions, mixed variable types, and imbalanced charge distributions reduce their analytical value. This study developed a reconstruction-aware framework for drug-crime charge classification from incomplete judicial records.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Drug-related judicial documents from Chengdu, China, covering 2014-2021 were screened, cleaned, and converted into structured person-level observations. The final dataset comprised 12,620 valid documents and 15,184 observations with 16 structured features. A Heterogeneous Graph Convolution Temporal Autoencoder (HetGConv-TAE) was developed to jointly model heterogeneous case-attribute relations and temporal changes in case composition. Performance was evaluated under 10%, 20%, and 30% controlled missingness, followed by XGBoost charge classification and SHAP interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>HetGConv-TAE achieved the best mean reconstruction performance across conventional, static graph, temporal, and relational graph baselines. XGBoost trained on HetGConv-TAE reconstructed data achieved weighted F1 scores close to 80% and ROC-AUC values above 90%. SHAP analysis identified drug weight, place category, and administrative district as the most influential predictors across charge categories.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Combining label-excluded heterogeneous graph reconstruction, temporal encoding, downstream classification, and interpretable analysis improves the analytical usefulness of incomplete judicial archives. The framework is intended to support data-quality assessment and aggregate public-safety research rather than automated legal decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdata.2026.1876811","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:33:05Z","timestamp":1788759185000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reconstruction-aware urban crime analytics from incomplete judicial records using heterogeneous graph temporal imputation"],"prefix":"10.3389","volume":"9","author":[{"given":"Wen","family":"Xu","sequence":"first","affiliation":[{"name":"Sichuan Police College","place":["Luzhou, Sichuan, China"]},{"name":"Intelligent Policing Key Laboratory of Sichuan Province","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Dai","sequence":"additional","affiliation":[{"name":"Sichuan Police College","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sichuan Police College","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Sichuan Police College","place":["Luzhou, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanxia","family":"Zeng","sequence":"additional","affiliation":[{"name":"Suining Traffic Police Detachment, Suining Public Security Bureau","place":["Suining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/2024.nllp-1.1","article-title":"\u201cLeGen: complex information extraction from legal sentences using generative models,\u201d","author":"Chaitra","year":"2024","journal-title":"Proceedings of the Natural Legal Language Processing Workshop 2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXGBoost: a scalable tree boosting system,\u201d","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B3","first-page":"25","article-title":"\u201cFilling the gaps: multivariate time series imputation by graph neural networks,\u201d","author":"Cini","year":"2022","journal-title":"Proceedings of the Tenth International Conference on Learning Representations, Virtual Event"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1977","DOI":"10.1057\/s41599-025-05924-3","article-title":"Large language models in legal systems: a survey","volume":"12","author":"Dehghani","year":"2025","journal-title":"Humanit. Soc. Sci. Commun."},{"key":"B5","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1080\/15389588.2022.2159763","article-title":"Exploring influences on the intention of motorcyclists to drink and ride: an investigation in a fourth-tier city of China","volume":"24","author":"Deng","year":"2023","journal-title":"Traffic Injury Prev."},{"key":"B6","doi-asserted-by":"publisher","first-page":"108552","DOI":"10.1016\/j.aap.2026.108552","article-title":"A comprehensive analysis of contributing factors in bus crashes: integrating passenger injury severity and vehicle damage severity using the Frank copula model","volume":"232","author":"Dong","year":"2026","journal-title":"Accident Anal. Prev."},{"key":"B7","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3390\/ijgi12060209","article-title":"A systematic review of multi-scale spatiotemporal crime prediction methods","volume":"12","author":"Du","year":"2023","journal-title":"ISPRS Int. J. Geo-Information"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2704","DOI":"10.1145\/3366423.3380027","article-title":"\u201cHeterogeneous graph transformer,\u201d","author":"Hu","year":"2020","journal-title":"Proceedings of the Web Conference 2020"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1007\/s12652-023-04530-y","article-title":"Machine learning in crime prediction","volume":"14","author":"Jenga","year":"2023","journal-title":"J. Ambient Intell. Humanized Comput."},{"key":"B10","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/s42154-025-00376-6","article-title":"Determinants of autonomous vehicle crashes in high-risk scenarios: a novel crash analysis framework","volume":"9","author":"Jin","year":"2026","journal-title":"Automotive Innov."},{"key":"B11","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1080\/15389588.2024.2312517","article-title":"Analysis of dynamic determinants of vehicles involved in crash affecting severity based on in-depth crash data","volume":"25","author":"Jin","year":"2024","journal-title":"Traffic Injury Prev."},{"key":"B12","doi-asserted-by":"publisher","first-page":"108274","DOI":"10.1016\/j.aap.2025.108274","article-title":"Zone-specific real-time traffic conflict risk modeling for freeway tunnels: a CrossTabNet approach","volume":"223","author":"Jin","year":"2025","journal-title":"Accident Anal. Prev."},{"key":"B13","doi-asserted-by":"publisher","first-page":"127001","DOI":"10.1016\/j.eswa.2025.127001","article-title":"TMF-GNN: Temporal matrix factorization-based graph neural network for multivariate time series forecasting with missing values","volume":"275","author":"Kim","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B14","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s40163-020-00116-7","article-title":"A systematic review on spatial crime forecasting","volume":"9","author":"Kounadi","year":"2020","journal-title":"Crime Sci."},{"key":"B15","doi-asserted-by":"publisher","first-page":"648","DOI":"10.3390\/electronics13030648","article-title":"A survey on challenges and advances in natural language processing with a focus on legal informatics and low-resource languages","volume":"13","author":"Krasadakis","year":"2024","journal-title":"Electronics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1198","DOI":"10.1080\/01621459.1988.10478722","article-title":"A test of missing completely at random for multivariate data with missing values","volume":"83","author":"Little","year":"1988","journal-title":"J. Am. Statistical Assoc."},{"key":"B17","first-page":"4765","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","volume-title":"Advances in Neural Information Processing Systems 30","author":"Lundberg","year":"2017"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1080\/15389588.2026.2654184","article-title":"Spatiotemporal analysis of urban traffic crash risk using a bagging-optimized dynamic mode decomposition framework","author":"Ma","year":"2026","journal-title":"Traffic Injury Prev."},{"key":"B19","doi-asserted-by":"publisher","first-page":"32069","DOI":"10.52202\/068431-2324","article-title":"\u201cLearning to reconstruct missing data from spatiotemporal graphs with sparse observations,\u201d","author":"Marisca","year":"2022","journal-title":"Advances in Neural Information Processing Systems 35"},{"key":"B20","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","article-title":"Inference and missing data","volume":"63","author":"Rubin","year":"1976","journal-title":"Biometrika"},{"key":"B21","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"\u201cModeling relational data with graph convolutional networks,\u201d","author":"Schlichtkrull","year":"2018","journal-title":"The Semantic Web: 15th International Conference, ESWC 2018, June 3\u20137, 2018, Proceedings"},{"key":"B22","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","article-title":"Missing value estimation methods for DNA microarrays","volume":"17","author":"Troyanskaya","year":"2001","journal-title":"Bioinformatics"},{"key":"B23","volume-title":"World Drug Report 2025.","year":"2025"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","article-title":"mice: Multivariate imputation by chained equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J. Statistical Softw."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1145\/3308558.3313562","article-title":"\u201cHeterogeneous graph attention network,\u201d","author":"Wang","year":"2019","journal-title":"The World Wide Web Conference"},{"key":"B26","first-page":"5689","article-title":"\u201cGAIN: missing data imputation using generative adversarial nets,\u201d","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Yoon","year":"2018"},{"key":"B27","doi-asserted-by":"publisher","first-page":"101789","DOI":"10.1016\/j.compenvurbsys.2022.101789","article-title":"Interpretable machine learning models for crime prediction","volume":"94","author":"Zhang","year":"2022","journal-title":"Computers, Environment and Urban Systems"},{"key":"B28","doi-asserted-by":"publisher","author":"Zhong","year":"2020","DOI":"10.18653\/v1\/2020.acl-main.466"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.3390\/su15032563","article-title":"Exploring the macro economic and transport influencing factors of urban public transport mode share: A Bayesian structural equation model approach","volume":"15","author":"Zhou","year":"2023","journal-title":"Sustainability"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1876811\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:33:07Z","timestamp":1788759187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1876811\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":29,"alternative-id":["10.3389\/fdata.2026.1876811"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2026.1876811","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"article-number":"1876811"}}