Generation Method Research Articles

Performance of Publicly Available Large Language Models on Internal Medicine Board-style Questions.

Ongoing research attempts to benchmark large language models (LLM) against physicians' fund of knowledge by assessing LLM performance on medical examinations. No prior study has assessed LLM performance on internal medicine (IM) board examination questions. Limited data exists on how knowledge supplied to the models, derived from medical texts improves LLM performance. The performance of GPT-3.5, GPT-4.0, LaMDA and Llama 2, with and without additional model input augmentation, was assessed on 240 randomly selected IM board-style questions. Questions were sourced from the Medical Knowledge Self-Assessment Program released by the American College of Physicians with each question serving as part of the LLM prompt. When available, LLMs were accessed both through their application programming interface (API) and their corresponding chatbot. Mode inputs were augmented with Harrison's Principles of Internal Medicine using the method of Retrieval Augmented Generation. LLM-generated explanations to 25 correctly answered questions were presented in a blinded fashion alongside the MKSAP explanation to an IM board-certified physician tasked with selecting the human generated response. GPT-4.0, accessed either through Bing Chat or its API, scored 77.5-80.7% outperforming GPT-3.5, human respondents, LaMDA and Llama 2 in that order. GPT-4.0 outperformed human MKSAP users on every tested IM subject with its highest and lowest percentile scores in Infectious Disease (80th) and Rheumatology (99.7th), respectively. There is a 3.2-5.3% decrease in performance of both GPT-3.5 and GPT-4.0 when accessing the LLM through its API instead of its online chatbot. There is 4.5-7.5% increase in performance of both GPT-3.5 and GPT-4.0 accessed through their APIs after additional input augmentation. The blinded reviewer correctly identified the human generated MKSAP response in 72% of the 25-question sample set. GPT-4.0 performed best on IM board-style questions outperforming human respondents. Augmenting with domain-specific information improved performance rendering Retrieval Augmented Generation a possible technique for improving accuracy in medical examination LLM responses.

High-value application of kaolin by wet mixing method in low heat generation and high wear-resistant natural rubber composites

In this study, a silane coupling agent and kaolin, a natural mineral resource, were introduced into the wet mixing process of natural rubber latex, the high wear-resistant and low-generation heat natural rubber composites were prepared. The sputtering, collision, and deposition of coupling agent/fillers/natural rubber latex mixed emulsion onto the roller effectively could break up the filler aggregates, enable fillers to be better infiltrated, distributed, and dispersed in the rubber. The effects of dry/wet mixing processes and the ratio of kaolin to silica on the crosslinking density, filler dispersion, extrusion rheological properties, gas barrier properties, dynamic mechanical properties and thermal stability of NR composites were investigated, and the silanization mechanism was summarized by FTIR and XRD. The experimental results showed that kaolin improved the crosslinking density and failure temperature, reduced the Payne effect, extrusion swell, and rolling resistance. Compared with 60 phr silica-filled natural rubber, the gas barrier property and wear resistance of 60 phr kaolin-filled natural rubber were improved by 64 % and 27 %, respectively, and the rolling resistance was reduced by 57 %. When the ratios of silica to kaolin were both 20:40, the crosslinking density, gas barrier property, and wear resistance of wet mixing were improved by 24 %, 45 %, and 9 %, respectively, compared with dry mixing. This study provided a new method for the high-value application of kaolin in wet mixing and green tires.

Memory-Based Learning and Fusion Attention for Few-Shot Food Image Generation Method

Generating food images aims to convert textual food ingredients into corresponding images for the visualization of color and shape adjustments, dietary guidance, and the creation of new dishes. It has a wide range of applications, including food recommendation, recipe development, and health management. However, existing food image generation models, predominantly based on GANs (Generative Adversarial Networks), face challenges in maintaining semantic consistency between image and text, as well as achieving visual realism in the generated images. These limitations are attributed to the constrained representational capacity of sparse ingredient embedding and the lack of diversity in GAN-based food image generation models. To alleviate this problem, this paper proposes a food image generation network, named MLA-Diff, in which ingredient and image features are learned and integrated as ingredient-image pairs to generate initial images, and then image details are refined by using an attention fusion module. The main contributions are as follows: (1) The enhanced CLIP (Contrastive Language-Image Pre-Training) module is constructed by transforming sparse ingredient embedding into compact embedding and capturing multi-scale image features, providing an effective solution to alleviate semantic consistency issues. (2) The Memory module is proposed by embedding a pre-trained diffusion model to generate initial images with diversity and reality. (3) The attention fusion module is proposed by integrating features from diverse modalities to enhance the comprehension between ingredient and image features. Extensive experiments on the Mini-food dataset demonstrate the superiority of the MLA-Diff in terms of semantic consistency and visual realism, generating high-quality food images.

Is It Hard to Generate Holistic Commit Message?

Commit messages are important for developers to understand the content and the reason for code changes. However, poor and even empty commit messages widely exist. To improve the quality of commit messages and development efficiency, many commit message generation methods have been proposed. Nevertheless, previous methods mainly focus on a brief generation problem, where both the input code change and the output commit messages are restricted to short. This may initiate a debate on the performance of these methods in practice. In this paper, we attempt to remove the restrictions and move the needle forward to a holistic commit message generation problem. In particular, we conduct experiments to evaluate the performance of existing commit message generation methods in holistic commit message generation. In the experiments, we choose seven state-of-the-art commit generation methods and focus on two important scenarios in commit message generation (i.e., the within-project scenario and the cross-project scenario). To conduct our experiments, we publish a holistic commit message dataset HORDA with test data manually labeled. In our evaluations, we find that in generating holistic commit messages, the IR-based method has a better performance than non-pre-trained generation-based methods in the within-project scenario, contradicting previous research findings. Further, while the pre-trained generation-based methods are better than non-pre-trained generation-based methods, they are still constrained by the limitations of generation models.

Comparing AIGC and traditional idea generation methods: Evaluating their impact on creativity in the product design ideation phase

In the early stages of product design, generating creative ideas is crucial for designers as it lays the groundwork for innovative products. This study explores how different idea generation methods, including modern artificial intelligence-generated content (AIGC) and traditional approaches, affect designers' creativity. Using a mixed-methods approach, we conducted a detailed experiment with 38 s-year university students majoring in product design, comparing four methods: traditional brainstorming (with and without images) and AIGC (using DCGANs and PGGANs). Our findings indicate that while AIGC offers benefits, it does not consistently surpass traditional techniques in fostering creativity. The quality of AIGC-generated images significantly impacts creativity, with higher-quality images proving more inspirational. Additionally, gender differences were observed: male designers preferred traditional methods, while female designers favored AIGC for creative enhancement. Male designers generated more creative ideas when working with low-quality images, whereas female designers were more productive with high-quality stimuli. This study suggests that to optimize creativity in product design, it is essential to balance the benefits of both AIGC and traditional methods, choosing the approach that best fits the project's unique needs rather than focusing solely on the latest or most advanced methods. Moreover, maintaining a good balance between AIGC and traditional idea generation methods throughout the process should be considered.

Recent advances of 5-endo-trig radical cyclization: promoting strategies and applications.

5-endo-trig radical cyclization has long been recognized as one of the most straightforward ways for the construction of densely functionalized five-membered rings. Nevertheless, according to Baldwin's rules, the 5-endo-trig radical cyclization is kinetically disfavored due to stereoelectronic effects and thus usually proceeds via a slow rate, which renders its application a challenging task. In recent years, with the emergence of efficient radical generation methods and effective cyclization strategies, 5-endo-trig radical cyclization has been successfully accelerated to a synthetically useful rate and has been utilized in the access of diverse five-membered carbo- and heterocyclic compounds. This review comprehensively summarizes the methodologies involving the 5-endo-trig radical cyclization process, with particular emphasis on the elucidation of the promoting strategies, which include the polar effect, geometrical constraints, spin delocalization effect, and persistent radical effect. Each of these strategies is discussed in detail, with illustrative examples from recent literature studies to highlight their practical applications and effectiveness. It is anticipated that the in-depth understanding of the 5-endo-trig radical cyclization provided by this review would inspire further innovation of this privileged reaction mode and expand its applications. Moreover, the potent ring-closure-promoting strategies revealed herein would also contribute to achieving other challenges of cyclizations with particular significance for organic synthesis.

Guiding Diffusion Models for Antibody Sequence and Structure Co-design with Developability Properties

Recent advances in deep generative methods have allowed antibody sequence and structure co-design. This study addresses the challenge of tailoring the highly variable complementarity-determining regions (CDRs) in antibodies to fulfill developability requirements. We introduce a guidance approach that integrates property information into the antibody design process using diffusion probabilistic models. This approach allows us to simultaneously design CDRs conditioned on antigen structures while considering critical properties like solubility and folding stability. Our property-guided diffusion model offers versatility by accommodating diverse property constraints, presenting a promising avenue for computational antibody design in therapeutic applications. Published by the American Physical Society 2024

A method for selecting the type of energy storage for power systems with high penetration of renewable energy with multi-application scenarios

Energy storage (ES) configurations effectively relieve regulatory pressure on power systems with a high penetration of renewable energy. However, it is difficult for a single ES type to satisfy the complex regulatory demands of a power system. There has been little research on the selection methods for multiple types of ES that meet the demands of multiple application scenarios of power systems. This study introduces a method for the selection of ES types for power systems with a high penetration of renewable energy to determine the optimal ES types for multi-application scenarios. First, a generation method for ES schemes is proposed based on K-means clustering and combination theory. Then, considering the demands of peak shaving, frequency regulation and reserve of power systems with high penetration of renewable energy, an optimisation model of the expected indices of the ES is constructed to meet the demands of multi-application scenarios. Finally, the comprehensive evaluation method for ES schemes based on the error mean and the selection method for optimal ES types based on projection technology are proposed. Numerical studies show that for the power system in the example whose demand coefficients for peak shaving, frequency regulation and reserve are 30.59 %, 26.29 % and 43.11 %, respectively, a combination of pumped storage and colloidal battery, lithium iron phosphate battery, or lithium titanate battery is the most suitable ES type for the power system. This study offers a reference for the selection of ES types when an ES is configured.

Target-Specific De Novo Peptide Binder Design with DiffPepBuilder.

Despite the exciting progress in target-specific de novo protein binder design, peptide binder design remains challenging due to the flexibility of peptide structures and the scarcity of protein-peptide complex structure data. In this study, we curated a large synthetic data set, referred to as PepPC-F, from the abundant protein-protein interface data and developed DiffPepBuilder, a de novo target-specific peptide binder generation method that utilizes an SE(3)-equivariant diffusion model trained on PepPC-F to codesign peptide sequences and structures. DiffPepBuilder also introduces disulfide bonds to stabilize the generated peptide structures. We tested DiffPepBuilder on 30 experimentally verified strong peptide binders with available protein-peptide complex structures. DiffPepBuilder was able to effectively recall the native structures and sequences of the peptide ligands and to generate novel peptide binders with improved binding free energy. We subsequently conducted de novo generation case studies on three targets. In both the regeneration test and case studies, DiffPepBuilder outperformed AfDesign and RFdiffusion coupled with ProteinMPNN, in terms of sequence and structure recall, interface quality, and structural diversity. Molecular dynamics simulations confirmed that the introduction of disulfide bonds enhanced the structural rigidity and binding performance of the generated peptides. As a general peptide binder de novo design tool, DiffPepBuilder can be used to design peptide binders for given protein targets with three-dimensional and binding site information.

High-risk powered two-wheelers scenarios generation for autonomous vehicle testing using WGAN

Objective Autonomous vehicles (AVs) have the potential to revolutionize the future of mobility by significantly improving traffic safety. This study presents a novel method for validating the safety performance of AVs in high-risk scenarios involving powered 2-wheelers (PTWs). By generating high-risk scenarios using in-depth crash data, this study is devoted to addressing the challenge of public road scenarios in testing, which often lack the necessary complexity and risk to effectively evaluate the capabilities of AVs in high-risk situations. Method Our approach employs a Wasserstein generative adversarial network (WGAN) to generate high-risk scenes, particularly focusing on PTW scenarios. By extracting 314 car-to-PTW crashes from the China In-depth Mobility Safety Study–Traffic Accident database, we simulate outcomes using PC-Crash software. The data are divided into scenes at 0.1-s intervals, with WGAN generating numerous high-risk scenes. By using a cumulative distribution function (CDF), we sampled and analyzed the vehicle’s dynamic information to generate complete scenarios applicable to the test. The validation process involves using the SVL Simulator and the Baidu Apollo joint simulation platform to evaluate the AV’s driving behavior and interactions with PTWs. Results This study evaluates model generation results by comparing distributions using Wasserstein distance as an indicator. The generator converges after approximately 200 epochs, with the iterator converging quickly. Subsequently, 10,000 new scenes are then generated. The distribution of several key parameters in the generated scenes can be found to approximate that of the original scenes. After sampling, the usability of generated scenarios is 64.76%. Virtual simulations confirm the effectiveness of the scenario generation method, with a generated scenario crash rate of 16.50% closely reflecting the original rate of 15.0%, showcasing the method’s capacity to produce realistic and hazardous scenarios. Conclusions The experimental results suggest that these scenarios exhibit a level of risk similar to the original crashes and are effective for testing AVs. Consequently, the generated scenarios enhance the diversity of the scenario library and accelerate the overall testing process of AVs.

Multiple-ResNet GAN: An enhanced high-resolution image generation method for translation from fundus structure image to fluorescein angiography.

Fluorescein angiography (FA) is a diagnostic method for observing the vascular circulation in the eye. However, it poses a risk to patients. Therefore, generative adversarial networks have been used to convert retinal fundus structure images into FA images. Existing high-resolution image generation methods employ complex deep network models that are challenging to optimize, which leads to issues such as blurred lesion boundaries and poor capture of microleakage and microvessels. In this study, we propose a multiple-ResNet generative adversarial network (GAN) to improve model training, thereby enhancing the ability to generate high-resolution FA images. First, the structure of the multiple-ResNet generator is designed to enhance detail generation in high-resolution images. Second, the Gaussian error linear unit (GELU) activation function is used to help the model converge rapidly. The effectiveness of the multiple-ResNet is verified using the publicly available Isfahan MISP dataset. Experimental results show that our method outperforms other methods, achieving better quantitative results with a mean structural similarity of 0.641, peak signal-to-noise ratio of 18.25, and learned perceptual image patch similarity of 0.272. Compared with state-of-the-art methods, the results showed that using the multiple-ResNet framework and GELU activation function can improve the generation of detailed regions in high-resolution FA images.

Precision strike: Precise backdoor attack with dynamic trigger

Deep neural networks have advanced significantly in the last several years and are now widely employed in numerous significant real-world applications. However, recent research has shown that deep neural networks are vulnerable to backdoor attacks. Under such attacks, attackers release backdoor models that achieve satisfactory performance on benign samples while behaving abnormally on inputs with predefined triggers. Successful backdoor attacks can have serious consequences, such as attackers using backdoor generation methods to bypass critical face recognition authentication systems. In this paper, we propose PBADT, a precise backdoor attack with dynamic trigger. Unlike existing work that uses static or random trigger masks, we design an interpretable trigger mask generation framework that places triggers at positions that have the most significant impact on the prediction results. Meanwhile, backdoor attacks are made more efficient by using forgettable events to improve the efficiency of backdoor attacks. The proposed backdoor method is extensively evaluated on three face recognition datasets, LFW, CelebA, and VGGFace, while further evaluated on two general image datasets, CIFAR-10 and GTSRB. Our approach achieves almost perfect attack performance on backdoor data.

An approach to generate cross-polarization modulation-enabled optical frequency comb with enhanced spectral flatness in traveling-wave semiconductor optical amplifiers

Abstract This paper proposes a method for generating an optical frequency comb (OFC) using the cross-polarization modulation (XPolM) effect in a traveling-wave semiconductor optical amplifier (TW-SOA). The TW-SOA acted as a lumped amplifier, enabling pulse generation within the comb. The proposed method of OFC generation achieved a comb spectrum with 51 lines and a maximum power deviation of 1.8 dB, indicating excellent spectral flatness. The proposed approach effectively utilized XPolM in a TW-SOA to create broad flat OFCs. The effectiveness of XPolM depends on various SOA parameters, such as pump and signal powers, and the confinement factor. To understand the XPolM-enabled OFC behavior, various parameters, such as input polarization, bias current, SOA confinement factor, and carrier density, have been optimized. These parameters significantly influenced the generated comb spectrum. This study also provides valuable insights into optimizing comb characteristics through theoretical analysis. The proposed OFC generation was simulated using an OptiSystem simulator. This has paved the way for the potential use of the comb as a multichannel source in various optical devices.

Brain tumoroids: treatment prediction and drug development for brain tumors with fast, reproducible and easy-to-use personalized models.

generation of patient avatar is critically needed in neuro-oncology for treatment prediction and preclinical therapeutic development. Our objective was to develop a fast, reproducible, low-cost and easy-to-use method of tumoroids generation and analysis, efficient for all types of brain tumors, primary and metastatic. tumoroids were generated from 89 patients: 81 primary tumors including 77 gliomas, and 8 brain metastases. Tumoroids morphology, cellular and molecular characteristics were compared with the ones of the parental tumor by using histology, methylome profiling, pTERT mutations and multiplexed spatial immunofluorescences. Their cellular stability overtime was validated by flow cytometry. Therapeutic sensitivity was evaluated and predictive factors of tumoroid generation were analyzed. All the tumoroids analyzed had similar histological (N=21) and molecular features (N=7) than the parental tumor. Median generation time was 5 days. Success rate was 65 %: it was higher for high grade gliomas and brain metastases versus IDH mutated low grade gliomas. For high-grade gliomas, neither other clinical, neuro-imaging, histological nor molecular factors were predictive of tumoroid generation success. The cellular organization inside tumoroids analyzed by MACSima revealed territories dedicated to specific cell subtypes. Finally, we showed the correlation between tumoroid and patient treatment responses to radio-chemotherapy and their ability to respond to immunotherapy thanks to a dedicated and reproducible 3D analysis workflow. patient-derived tumoroid model that we developed offers a robust, user-friendly, low-cost and reproducible preclinical model valuable for therapeutic development of all type of primary or metastatic brain tumors, allowing their integration into forthcoming early-phase clinical trials.

APMG: 3D Molecule Generation Driven by Atomic Chemical Properties.

Recently, mask-fill-based 3D Molecular Generation (MG) methods have become very popular in virtual drug design. However, the existing MG methods ignore the chemical properties of atoms and contain inappropriate atomic position training data, which limits their generation capability. To mitigate the above issues, this paper presents a novel mask-fill-based 3D molecule generation model driven by atomic chemical properties (APMG). Specifically, we construct a new attention-MPNN-based encoder and introduce the electronic information into atom representations to enrich chemical properties. Also, a multi-functional classifier is designed to predict the electronic information of each generated atom, guiding the type prediction of elements and bonds. By design, the proposed method uses the chemical properties of atoms and their correlations for high-quality molecule generation. Second, to optimize the atomic position training data, we propose a novel atomic training position generation approach using the Chi-Square distribution. We evaluate our APMG method on the CrossDocked dataset and visualize the docking states of the pockets and generated molecules. The obtained results demonstrate the superiority and merits of APMG over the state-of-the-art approaches. The dataset and codes will be available on the project homepage: https://github.com/JU-HuaY/APMG.

A high‐precision timing and frequency synchronization algorithm for multi‐h CPM signals

AbstractIn the context of certain specific digital communication systems, where there are limitations such as spectral resources and energy availability, continuous phase modulation (CPM) emerges as an appealing choice among various modulation methods. Among CPM signals, multi‐h CPM is particularly noteworthy for its ability to address these constraints within the realm of single‐carrier and constant‐envelope waveforms. At the physical layer, the design of a multi‐h CPM receiver necessitates the efficient implementation of timing and frequency synchronization algorithm within a high dynamic environment. So this paper presents an innovative approach for achieving timing and frequency synchronization. To rectify timing offset and mitigate the adverse effects of noise in received signals, a re‐configurable local filter generation method is integrated into the timing synchronization algorithm. Simultaneously, an enhanced least mean square adaptive filter algorithm is applied to address frequency synchronization. A comprehensive series of simulations rigorously evaluates the outcomes of proposed novel synchronization methodology. These analyses demonstrate a notable proximity between the synchronization errors of proposed algorithm in this paper and the performance benchmark set by the modified Cramer–Rao bound. The proposed synchronization technology also exhibits the capability to substantially reduce the bit error rate, thereby effectively enhancing demodulation performance in multi‐h CPM receivers.

RT-SNDETR: real-time supernova detection via end-to-end image transformers

ABSTRACT In large-scale astronomical surveys, traditional supernova detection pipelines rely on complex and relatively inefficient image differencing techniques. This paper proposes an end-to-end deep-learning supernova detection network, the Real-Time SuperNova DEtection TRansformer (RT-SNDETR). This network partially replaces traditional pipelines by integrating image differencing, source detection, and Real-bogus classification, achieving a speed 51.49 times that of the fastest image differencing method, SFFT. Additionally, it remains competitive with methods like YOLO v8, offering a well-balanced trade-off between speed and accuracy. Experimental results highlight RT-SNDETR’s superior performance, with an average precision(AP) of 96.30 per cent on synthetic samples and 76.60 per cent on real supernova samples. It significantly outperforms other detection networks, including RT-DETR (+5.6 per cent AP on synthetic/+5.1 per cent AP on real samples) and Cascade R-CNN (+8.9 per cent AP on synthetic/ +28.6 per cent AP on real samples). The incorporation of CycleGAN-based data generation methods plays a significant role in enhancing RT-SNDETR’s performance. These methods simulate realistic PSF variations, enabling the object detection network to learn more robust features and improving its generalization to real supernovae data. Additionally, by integrating unsupervised domain adaptation techniques, RT-SNDETR achieves an AP of 81.70 per cent on real SDSS supernova survey samples. This study demonstrates RT-SNDETR’s potential to significantly enhance both the speed and accuracy of supernova detection, making it a highly effective solution for large-scale astronomical surveys.

Towards similar alignment and unique uniformity in collaborative filtering

Representation learning, with its desired properties, including Alignment and Uniformity, has recently emerged as an effective approach in collaborative filtering (CF) for recommender systems. Alignment measures the distance between positive pairs, and uniformity describes the distribution of all samples on the unit hypersphere. Despite the effectiveness of existing research, the challenges of insufficient alignment and uniformity bias persist in studies on the desired properties of recommender systems: (1) Sparse interaction information leads to an insufficient alignment representation. (2) Calculating the uniformity loss based on duplicate samples introduces bias, which affects the overall representation uniformity.Building on aforementioned challenges, we propose a Similar Alignment and Unique Uniformity model called SUAU. SUAU mitigates insufficient alignment by introducing additional item-similar item pairs for model training and employing a uniqueness strategy to prevent uniformity bias. More specifically, we propose a similar items generation method that identifies the most similar items based on the interaction behavior of the original items’ related users to form item-similar item pairs. The experimental results obtained on three highly sparse datasets demonstrate that the propose model achieves superior alignment and uniformity compared with state-of-the-art models, notably surpassing the best CF methods in terms of recommendation performance. We have open-sourced the source code on a publicly accessible website: https://github.com/ZzYUuuu/SUAU.

RESEARCH ON THE CONSTRUCTION OF AI COMPOSITION SYSTEM BASED ON HMM

The Markov chain is an automatic accompaniment algorithm for intelligent computer systems, belonging to the interdisciplinary research field of musicology and computer science. Currently, there are many methods for AI music generation, but research on AI music generation based on the Hidden Markov Model (HMM) is relatively scarce. This paper proposes a method for constructing an AI composition system based on the HMM. This system achieves the goal of automatically generating accompaniment music from score data. The proposed system has achieved relatively stable results in the generation of musical elements such as form and harmony, accompaniment texture, and instrumentation, and has scored well in evaluation experiments.

Does Differentially Private Synthetic Data Lead to Synthetic Discoveries?

Synthetic data have been proposed as a solution for sharing anonymized versions of sensitive biomedical datasets. Ideally, synthetic data should preserve the structure and statistical properties of the original data, while protecting the privacy of the individual subjects. Differential Privacy (DP) is currently considered the gold standard approach for balancing this trade-off. The aim of this study is to investigate how trustworthy are group differences discovered by independent sample tests from DP-synthetic data. The evaluation is carried out in terms of the tests' Type I and Type II errors. With the former, we can quantify the tests' validity, i.e., whether the probability of false discoveries is indeed below the significance level, and the latter indicates the tests' power in making real discoveries. We evaluate the Mann-Whitney U test, Student's t-test, chi-squared test, and median test on DP-synthetic data. The private synthetic datasets are generated from real-world data, including a prostate cancer dataset (n = 500) and a cardiovascular dataset (n = 70,000), as well as on bivariate and multivariate simulated data. Five different DP-synthetic data generation methods are evaluated, including two basic DP histogram release methods and MWEM, Private-PGM, and DP GAN algorithms. A large portion of the evaluation results expressed dramatically inflated Type I errors, especially at levels of ϵ ≤ 1. This result calls for caution when releasing and analyzing DP-synthetic data: low p-values may be obtained in statistical tests simply as a byproduct of the noise added to protect privacy. A DP Smoothed Histogram-based synthetic data generation method was shown to produce valid Type I error for all privacy levels tested but required a large original dataset size and a modest privacy budget (ϵ ≥ 5) in order to have reasonable Type II error levels.