DilatedFormer: dilated granularity transformer network for placental maturity grading in ultrasound
Open accessThe DOI matches its Crossref record; 47 of the 60 references it cites were found in a registry or an index; 26 of the 44 sources its claims cite were checked for support.
Abstract
Placental maturity grading is often utilized for evaluating fetal growth and maternal health. The paper presents a dilated granularity transformer network and verifies it on 500 ultrasound images.
Overview
CoChat Summary
TL;DR
The paper introduces DilatedFormer, an end-to-end transformer-based network for placental maturity grading (PMG) in ultrasound that uses dilated self-attention, a detail-specific feed-forward layer, and a feature pyramid decoder. On a dataset of 500 annotated ultrasound images, it reports better performance than compared methods, reaching 0.89 accuracy, 0.9574 Cohen’s kappa, and 0.9022 F1-score.
Key findings
- The collected dataset contains 500 ultrasound images: 128 Grade I, 115 Grade II, 122 Grade III, and 135 Grade IV.
- On the test setup described, DilatedFormer achieved 0.89 accuracy, 0.9574 Cohen’s kappa, and 0.9022 F1-score, outperforming all compared methods.
- Compared with the best-performing baselines among the listed methods, the paper reports improvement from 0.85 to 0.89 in accuracy, from 0.9407 to 0.9574 in Cohen’s kappa, and from 0.8921 to 0.9022 in F1-score.
- Ablation results show the full model (“Basic + DSA + FPD + Detail-specific”) improved over the baseline (“Basic”) from 0.85 to 0.89 accuracy, 0.9365 to 0.9574 kappa, and 0.8904 to 0.9022 F1-score.
Methods
- The model is a four-stage transformer architecture with dilated transformer blocks using multi-head dilated self-attention, a detail-specific feed-forward network, and a feature pyramid decoder for PMG prediction.
- The study uses a collected and annotated ultrasound dataset of 500 images, taken from the anterior wall placenta using GE Voluson E8 Expert/Phillip EPIQ7 systems; images were split into 400 training and 100 test images.
- Training used PyTorch, Adam, 80 epochs, initial learning rate 1×10^-4, batch size 16, input size 224×224, and evaluation used accuracy, Cohen’s kappa, and F1-score.
Limitations
- The paper states that the model is trained on ultrasound images with the same intensity distribution in a fully supervised fashion, and performance may degrade at new clinical sites due to vendor variability.
- The authors state future work is needed to make the model more lightweight and improve computational complexity.
- The text also suggests a limitation in data efficiency/generalization, since the authors say they should develop a more generalizable algorithm and incorporate multi-modality information such as clinical data.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
14 Valid · 1 Not valid · 7 Not checked · 24 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Inspired by [41], we introduced a feature pyramid decoder (FPD) to better aggregate multi-resolution features at different network levels for grading the placental maturity.”
What the sources say
- Supportedcites [41] Tian, 2019, Fcos: fully convolutional one-stage object detection source
Section 3.2 describes FCOS using a feature pyramid with top-down connections and feature maps at multiple network levels. That supports the cited inspiration for the authors’ decoder; introducing the decoder and applying it to placental-maturity grading are the citing authors’ own work, not claims attributed to FCOS. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Since the pooled feature extracted by a single scale in PVT is less powerful, we equipped self-attention with parallel dilated convolutions with different dilated rates and scales to better detect multi-grain objects in one cohort.”
What the sources say
- Partly supportedcites [21] Wang, 2021, Pyramid vision transformer: a versatile backbone for dense prediction without convolutions sourceExperimental — accuracy not yet measured
Section 3.3 (page unavailable) describes PVT’s spatial-reduction attention, which reduces the spatial scale of keys and values before attention. It does not say that the resulting feature is less powerful. Section 3.5 (page unavailable) also states that PVT generates multi-scale feature maps overall, so the paper does not establish the cited sentence’s assessment of PVT. (LLM, conf=0.78)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The existing methods often utilize a single fully connected layer as the classi fi cation head [21, 24, 26], thereby generating less reliable prediction for dilated granularity grading.”
What the sources say
- Supportedcites [21] Wang, 2021, Pyramid vision transformer: a versatile backbone for dense prediction without convolutions source
Section 4.1 (Image-Level Prediction) says PVT follows ViT and DeiT in using a fully connected layer for classification, supporting the cited description of this classification-head design. The citation is attached to that design claim; the subsequent judgment about reliability for dilated granularity grading is the citing authors’ own conclusion. (LLM, conf=0.86)
- Supportedcites [24] Dosovitskiy, 2020 source
Section 3.2 (p. 4) says ViT fine-tuning replaces the prediction head with a single D × K feedforward layer, supporting this citation’s role as an example of a single-layer classification head. The statement about less reliable dilated-granularity grading follows the citation and is the citing authors’ conclusion, not a finding attributed to this source. (LLM, conf=0.87)
- Supportedcites [26] Liu, 2021, Swin transformer: hierarchical vision transformer using shifted windows source
The citation is attached to the description of the classification head. In A2.1, the paper says its image classifier uses global average pooling followed by a linear classifier, so it serves as an example of the cited head design. The subsequent statement about grading reliability is the citing authors’ conclusion, not a finding attributed to this source. (LLM, conf=0.87)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“From these quantitative results, we can fi nd that ' basic +DSA ' has an accuracy improvement of 0.02, a Cohen ' s kappa improvement of 0.0115 over ' basic, ' and an F1-score improvement of 0.0060 (i.e., PVT [21]).”
What the sources say
- Supportedcites [21] Wang, 2021, Pyramid vision transformer: a versatile backbone for dense prediction without convolutions source
The Introduction identifies this paper as introducing Pyramid Vision Transformer (PVT), so the citation supports identifying the cited baseline as PVT. The 0.0060 F1-score improvement is presented as the citing authors’ own quantitative result, not as a result reported by this source. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“From these quantitative results, we can fi nd that ' basic +DSA ' has an accuracy improvement of 0.02, a Cohen ' s kappa improvement of 0.0115 over ' basic, ' and an F1-score improvement of 0.0060 (i.e., PVT [21]).”
What the sources say
- Supportedcites [21] Wang, 2021, Pyramid vision transformer: a versatile backbone for dense prediction without convolutions source
The citation identifies the citing study’s ‘basic’ baseline as PVT, rather than attributing the DSA accuracy gain to the source. The Introduction identifies the source’s model as Pyramid Vision Transformer (PVT); the reported 0.02 gain is the citing study’s own result. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
17 more claims · 2 with their cited sources checked
Create a free account to see all 46 claims and to verify the 2 references still open.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 17
- The quote only partly states this claim. 1
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738
Rethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517
FCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259
Self-citationTransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., & Zhou, Y. (2021) · arXiv · doi:10.48550/arxiv.2102.04306 · Cited by 4,206
Gaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537
DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
Tola, E., Lepetit, V., & Fua, P. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.77 · Cited by 1,405
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Qiao, S., Chen, L.-C., & Yuille, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01008 · Cited by 1,245
DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation
Lin, A., Chen, B., Xu, J., Zhang, Z., Lu, G., & Zhang, D. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3178991 · Cited by 882
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
Li, Y., Wu, C.-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00476 · Cited by 812
The ultrasonic changes in the maturing placenta and their relation to fetal pulmonic maturity
Grannum, P. A. T., Berkowitz, R. L., & Hobbins, J. C. (1979) · American Journal of Obstetrics and Gynecology · doi:10.1016/0002-9378(79)90312-0 · Cited by 408
Prenatal diagnosis of placenta previa accreta by transabdominal color Doppler ultrasound
Chou, M. M., Ho, E. S. C., & Lee, Y. H. (2000) · Ultrasound in Obstetrics & Gynecology · doi:10.1046/j.1469-0705.2000.00018.x · Cited by 284
Deep convolutional neural networks for mammography: advances, challenges and applications
Abdelhafiz, D., Yang, C., Ammar, R., & Nabavi, S. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2823-4 · Cited by 274
The preterm birth syndrome: issues to consider in creating a classification system
Goldenberg, R. L., Gravett, M. G., Iams, J., Papageorghiou, A. T., Waller, S. A., Kramer, M., Culhane, J., Barros, F., Conde-Agudelo, A., Bhutta, Z. A., et al. (2012) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2011.10.865 · Cited by 235
Prostate cancer detection using deep convolutional neural networks
Yoo, S., Gujrathi, I., Haider, M. A., & Khalvati, F. (2019) · Scientific Reports · doi:10.1038/s41598-019-55972-4 · Cited by 230
Vision Transformers for Classification of Breast Ultrasound Images
Gheflati, B., & Rivaz, H. (2022) · 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871809 · Cited by 225
Zhu, X., Suk, H.-I., Wang, L., Lee, S.-W., & Shen, D. (2017) · Medical Image Analysis · doi:10.1016/j.media.2015.10.008 · Cited by 224
Zhu, X., Suk, H.-I., & Shen, D. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.05.078 · Cited by 202
Training data-efficient image transformers & distillation through attention
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., & Jégou, H. (2020) · arXiv · doi:10.48550/arxiv.2012.12877 · Cited by 182
A modified deep convolutional neural network for abnormal brain image classification
Hemanth, D. J., Anitha, J., Naaji, A., Geman, O., Popescu, D. E., & Hoang Son, L. (2019) · IEEE Access · doi:10.1109/access.2018.2885639 · Cited by 164
Method for diagnosis of acute lymphoblastic leukemia based on vit-cnn ensemble model
Jiang, Z., Dong, Z., Wang, L., & Jiang, W. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/7529893 · Cited by 124
Forecasting covid-19 new cases using deep learning methods
Xu, L., Magar, R., & Barati Farimani, A. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105342 · Cited by 105
Liu, G., Ding, Q., Luo, H., Sha, M., Li, X., & Ju, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106194 · Cited by 81
Self-citationScaled ReLU Matters for Training Vision Transformers
Wang, P., Wang, X., Luo, H., Zhou, J., Zhou, Z., Wang, F., Li, H., & Jin, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20150 · Cited by 65
Self-citationUltrasound of the Placenta and Umbilical Cord: A Review
Kellow, Z. S., & Feldstein, V. A. (2011) · Ultrasound Quarterly · doi:10.1097/ruq.0b013e318229ffb5 · Cited by 55
Background selection schema on deep learning-based classification of dermatological disease
Zhou, J., Wu, Z., Jiang, Z., Huang, K., Guo, K., & Zhao, S. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105966 · Cited by 53
Dubiel, M., Breborowicz, G. H., Ropacka, M., Pietryga, M., Maulik, D., & Gudmundsson, S. (2005) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2004.12.008 · Cited by 36
Fundus Disease Image Classification based on Improved Transformer
Yang, H., Chen, J., & Xu, M. (2021) · 2021 International Conference on Neuromorphic Computing (ICNC) · doi:10.1109/icnc52316.2021.9608181 · Cited by 31
Novel placental ultrasound assessment: Potential role in pre-gestational diabetic pregnancy
Moran, M., Mulcahy, C., Daly, L., Zombori, G., Downey, P., & McAuliffe, F. M. (2014) · Placenta · doi:10.1016/j.placenta.2014.03.007 · Cited by 24
Covid-19 automatic diagnosis with ct images using the novel transformer architecture
Costa, G. S. S., Paiva, A. C., Braz Júnior, G., & Ferreira, M. M. (2021) · Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS 2021) · doi:10.5753/sbcas.2021.16073 · Cited by 24
Automatic staging of placental maturity based on dense descriptor
Li, X., Yao, Y., Ni, D., Chen, S., Li, S., Lei, B., & Wang, T. (2014) · Bio-Medical Materials and Engineering · doi:10.3233/bme-141100 · Cited by 12
Multi-modal and multi-layout discriminative learning for placental maturity staging
Lei, B., Li, W., Yao, Y., Jiang, X., Tan, E.-L., Qin, J., Chen, S., Ni, D., & Wang, T. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.09.037 · Cited by 12
Automatic grading of placental maturity based on LIOP and fisher vector
Lei, B., Li, X., Yao, Y., Li, S., Chen, S., Zhou, Y., Ni, D., & Wang, T. (2014) · 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc.2014.6944666 · Cited by 8
Automatic placental maturity grading via hybrid learning
Lei, B., Tan, E.-L., Chen, S., Li, W., Ni, D., Yao, Y., & Wang, T. (2017) · Neurocomputing · doi:10.1016/j.neucom.2016.10.033 · Cited by 5
Verenich, E., Martin, T., Velasquez, A., Khan, N., & Hussain, F. (2021) · arXiv · doi:10.48550/arxiv.2109.00573 · Cited by 4
Hybrid descriptor for placental maturity grading
Lei, B., Jiang, F., Zhou, F., Ni, D., Yao, Y., Chen, S., & Wang, T. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08489-x · Cited by 3
Cited by
Multi-view co-occurrence and dual-modality framework for breast cancer classification
Su, C., Gong, Z., & Cao, J. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00096-1 · Cited by 5
Liu, Z. L., Zhang, Z., & Li, S. (2026) · Agriculture · doi:10.3390/agriculture16080875 · Cited by 3
Metadata
- Authors
- Wu, Y., Yang, Y., Zhu, L., Han, Z., Luo, H., Xue, X., & Wang, W.
- Affiliations
- Sichuan University (CN)
- The Hong Kong University of Science and Technology (Guangzhou) (CN)
- Third Affiliated Hospital of Sun Yat-sen University (CN)
- Jiangxi University of Water Resources and Electric Power (CN)
- Hong Kong Metropolitan University (HK)
- Corresponding author
- Luo, Hong
- Venue
- Frontiers in Physics
- Publisher
- Frontiers Media SA
- Published
- 2023-09-04
- Volume
- 11
- ISSN
- 2296-424X (ISSN-L)
- OpenAlex
- W4386417425
- Semantic Scholar
- b4d491f8d0a6b50845bf3198e607479996cf4581
- Cited by
- 2
- References
- 60
- Citations by year
- 2026: 1 · 2025: 1
- FWCI
- 0.15
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Physics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- ultrasound images, end-to-end learning, fetal growth assessment, medical image classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.