Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture
The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.
Abstract
Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“They show that our method instantiated with Fast R-CNN and Faster R-CNN outperforms the approach based on knowledge distillation [53] consistently, in terms of both the final performance and the performance drop compared with the upper bounds.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“The gap between the solid lines is almost always larger than that of the dashed lines, which means our mAP drop is consistently less than ILOD [8].”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“it still suffers from catastrophic forgetting when directly applied to object detection as reported in [8].”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“our results surpass the previous best [8], [21], [22], [23] in terms of both the final performance and the performance gap compared with the joint training upper bound.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“Compared with ILOD [8], our IncDet achieves much less performance drop in both in-dataset and cross-dataset scenarios.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Common approaches, which have the advantage of easy implementation and outstanding efficiency, for feature selection include variable ranking [28], feature subset selection [29], penalized least squares [30], random feature extractions such as nonadaptive random projections [31] and random forest [32], or convolution-…”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“2716952 the most popular deep networks are the deep belief networks (DBN) [5], [6], the deep Boltzmann machines (DBM) [7], and the convolutional neural networks (CNN) [8], [9].”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 6×
“Specifically, if the function in the feature mapping uses convolutional functions, the broad learning network structure is very similar to that of classical CNN structure except that the broad learning network has additional connecting links between the convolutional layers and the output layer.”
BackgroundMethodInfluentialGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 7×
“2716952 the most popular deep networks are the deep belief networks (DBN) [5], [6], the deep Boltzmann machines (DBM) [7], and the convolutional neural networks (CNN) [8], [9].”
BackgroundInfluentialRegression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“The above problem denoted by lasso in [45] is convex.”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 6×
“Parameters of RBM are referred to [5], i.”
BackgroundMethodInfluentialBoyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952 · cited 2×
“Moreover, it has been shown that many state-of-art algorithms for l1 norm involved problems could be derived by ADMM [50], such as FISTA.”
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
Tropp, J. A., & Gilbert, A. C. (2007) · IEEE Transactions on Information Theory · doi:10.1109/tit.2007.909108 · Cited by 9,653 · cited 1×
“Consequently, the approximation problem in (4) can be solved by dozens of ways, such as orthogonal matching pursuit [46], K-SVD [47], alternating direction method of multipliers (ADMM) [48], and fast iterative shrinkage-thresholding algorithm (FISTA) [49].”
Method$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,451 · cited 1×
“Consequently, the approximation problem in (4) can be solved by dozens of ways, such as orthogonal matching pursuit [46], K-SVD [47], alternating direction method of multipliers (ADMM) [48], and fast iterative shrinkage-thresholding algorithm (FISTA) [49].”
MethodVariable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Fan, J., & Li, R. (2001) · Journal of the American Statistical Association · doi:10.1198/016214501753382273 · Cited by 8,900 · cited 1×
“Common approaches, which have the advantage of easy implementation and outstanding efficiency, for feature selection include variable ranking [28], feature subset selection [29], penalized least squares [30], random feature extractions such as nonadaptive random projections [31] and random forest [32], or convolution-…”
BackgroundPattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,265
(2006) · Springer eBooks · Cited by 8,123
Identification and control of dynamical systems using neural networks
Narendra, K. S., & Parthasarathy, K. (1990) · IEEE Transactions on Neural Networks · doi:10.1109/72.80202 · Cited by 8,014
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · cited 1×
“To prove the effectiveness of BLS, we will compare the classification ability of our method with existing mainstream methods, including stacked auto encoders (SAE) [6], another version of stacked autoencoder (SDA) [52], DBN [5], multilayer perceptron-based methods (MLP) [53], DBM [7], two kinds of extremely learning m…”
MethodGeneralized Inverses: Theory and Applications
Rohatgi, V. K., Ben-Israel, A., & Greville, T. N. E. (1976) · International Statistical Review / Revue Internationale de Statistique · doi:10.2307/1403291 · Cited by 4,506 · cited 1×
“Generally, this model was inspired by the pseudoinverse of a partitioned matrix described in [37] and [38].”
Method(1989) · neural information processing systems · Cited by 3,736
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Data-intensive applications, challenges, techniques and technologies: A survey on Big Data
Philip Chen, C. L., & Zhang, C.-Y. (2014) · Information Sciences · doi:10.1016/j.ins.2014.01.015 · Cited by 3,047 · cited 2×
“However, a direct solution is too expensive, especially the training samples and input patterns are suffered from high volume, high velocity, and/or high variety [26].”
BackgroundSalakhutdinov, R., & Hinton, G. E. (2009) · International Conference on Artificial Intelligence and Statistics · Cited by 2,605
Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80131-5 · Cited by 2,121 · cited 1×
“Single layer feedforward neural networks (SLFN) have been widely applied to solve problems such as classification and regression because of their universal approximation capability [18]–[21].”
MethodExtreme Learning Machine for Multilayer Perceptron
Tang, J., Deng, C., & Huang, G.-B. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2424995 · Cited by 1,451 · cited 8×
“To prove the effectiveness of BLS, we will compare the classification ability of our method with existing mainstream methods, including stacked auto encoders (SAE) [6], another version of stacked autoencoder (SDA) [52], DBN [5], multilayer perceptron-based methods (MLP) [53], DBM [7], two kinds of extremely learning m…”
BackgroundMethodInfluentialLearning methods for generic object recognition with invariance to pose and lighting
LeCun, Y., Huang, F. J., & Bottou, L. (2004) · Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. · doi:10.1109/cvpr.2004.1315150 · Cited by 1,324
A Branch and Bound Algorithm for Feature Subset Selection
Narendra, & Fukunaga (1977) · IEEE Transactions on Computers · doi:10.1109/tc.1977.1674939 · Cited by 1,245 · cited 1×
“Common approaches, which have the advantage of easy implementation and outstanding efficiency, for feature selection include variable ranking [28], feature subset selection [29], penalized least squares [30], random feature extractions such as nonadaptive random projections [31] and random forest [32], or convolution-…”
BackgroundLearning and generalization characteristics of the random vector functional-link net
Pao, Y.-H., Park, G.-H., & Sobajic, D. J. (1994) · Neurocomputing · doi:10.1016/0925-2312(94)90053-1 · Cited by 1,138 · cited 2×
“RVFLNN effectively eliminates the drawback of the long training process and also it provides the generalization capability in function approximation [20], [24].”
Background$L_{1/2}$ Regularization: A Thresholding Representation Theory and a Fast Solver
Xu, Z., Chang, X., Xu, F., & Zhang, H. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2197412 · Cited by 1,062 · cited 1×
“Specifically, sparse feature learning models have been attractive that could explore essential characterization [12], [42], [43].”
BackgroundStochastic choice of basis functions in adaptive function approximation and the functional-link net
Igelnik, B., & Pao, Y.-H. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.471375 · Cited by 955 · cited 3×
“The random vector functional-link neural network (RVFLNN), proposed in [19]–[21], offers a different learning method.”
BackgroundMethodFunctional-link net computing: theory, system architecture, and functionalities
Pao, Y.-H., & Takefuji, Y. (1992) · Computer · doi:10.1109/2.144401 · Cited by 927 · cited 2×
“The random vector functional-link neural network (RVFLNN), proposed in [19]–[21], offers a different learning method.”
BackgroundRidge Regression: Biased Estimation for Nonorthogonal Problems
Hoerl, A. E., & Kennard, R. W. (2000) · Technometrics · doi:10.1080/00401706.2000.10485983 · Cited by 808 · cited 3×
“Consequently, we have W = (λI + AAT )−1 AT Y .”
MethodInfluentialFast Alternating Direction Optimization Methods
Goldstein, T., O'Donoghue, B., Setzer, S., & Baraniuk, R. (2014) · SIAM Journal on Imaging Sciences · doi:10.1137/120896219 · Cited by 785 · cited 4×
“Moreover, it has been shown that many state-of-art algorithms for l1 norm involved problems could be derived by ADMM [50], such as FISTA.”
BackgroundInfluentialVariable selection using svm based criteria
Rakotomamonjy, A. (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944977 · Cited by 712
Extreme Learning Machines [Trends & Controversies]
Cambria, E., Huang, G.-B., Kasun, L. L. C., Zhou, H., Vong, C. M., Lin, J., Yin, J., Cai, Z., Liu, Q., Li, K., et al. (2013) · IEEE Intelligent Systems · doi:10.1109/mis.2013.140 · Cited by 710
Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks
Gong, M., Zhao, J., Liu, J., Miao, Q., & Jiao, L. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2435783 · Cited by 638 · cited 1×
“DEEP structure neural networks and learnings have been applied in many fields and have achieved breakthrough successes in a great number of applications [1], [2], particularly in large scale data processing [3], [4].”
BackgroundA literature survey of low‐rank tensor approximation techniques
Grasedyck, L., Kressner, D., & Tobler, C. (2013) · GAMM-Mitteilungen · doi:10.1002/gamm.201310004 · Cited by 577 · cited 1×
“In [33] and [34], comprehensive exposition of the theory, algorithms, and applications of structured low-rank approximations are presented.”
BackgroundMarginalized Denoising Autoencoders for Domain Adaptation
Chen, M., Xu, Z., Weinberger, K. Q., & Sha, F. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.4683 · Cited by 498
高橋, 安., Rabins, M. J., & Auslander, D. M. (1970) · Addison-Wesley Longman Publishing Co., Inc. eBooks · Cited by 452
Random Projections of Smooth Manifolds
Baraniuk, R. G., & Wakin, M. B. (2009) · Foundations of Computational Mathematics · doi:10.1007/s10208-007-9011-z · Cited by 404 · cited 1×
“Common approaches, which have the advantage of easy implementation and outstanding efficiency, for feature selection include variable ranking [28], feature subset selection [29], penalized least squares [30], random feature extractions such as nonadaptive random projections [31] and random forest [32], or convolution-…”
BackgroundBlind Image Quality Assessment via Deep Learning
Hou, W., Gao, X., Tao, D., & Li, X. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2336852 · Cited by 368 · cited 1×
“DEEP structure neural networks and learnings have been applied in many fields and have achieved breakthrough successes in a great number of applications [1], [2], particularly in large scale data processing [3], [4].”
BackgroundGENERALIZED INVERSE OF A MATRIX AND ITS APPLICATIONS
Rao, C. R. (1972) · Theory of Statistics · doi:10.1525/9780520325883-032 · Cited by 346 · cited 1×
“Different methods can be used to calculate this generalized inverse, such as orthogonal projection method, orthogonalization method, iterative method, and SVD [39], [40].”
MethodChen, C. L. P., & Wan, J. Z. (1999) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/3477.740166 · Cited by 230 · cited 4×
“Illustration of stepwise update algorithm [27].”
MethodInfluentialSelf-citationFuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning
Chen, C. L. P., Zhang, C.-Y., Chen, L., & Gan, M. (2015) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2015.2406889 · Cited by 224
Self-citationLow Rank Approximation: Algorithms, Implementation, Applications
Markovsky, I. (2012) · Communications and Control Engineering · doi:10.1007/978-1-4471-2227-2 · Cited by 209
A Multiobjective Sparse Feature Learning Model for Deep Neural Networks
Gong, M., Liu, J., Li, H., Cai, Q., & Su, L. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2469673 · Cited by 198 · cited 2×
“Specifically, sparse feature learning models have been attractive that could explore essential characterization [12], [42], [43].”
BackgroundIncremental Semi-Supervised Clustering Ensemble for High Dimensional Data Clustering
Yu, Z., Luo, P., You, J., Wong, H.-S., Leung, H., Wu, S., Zhang, J., & Han, G. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2015.2499200 · Cited by 187
A rapid supervised learning neural network for function interpolation and approximation
Chen, C. L. P. (1996) · IEEE Transactions on Neural Networks · doi:10.1109/72.536316 · Cited by 169 · cited 3×
“In this section, first, the proposed broad learning is introduced based on the rapid and dynamic learning features of the functional-link network developed by Chen and Wan [27] and Chen [36].”
Self-citationNeural Network Recognizer for Hand-Written Zip Code Digits
Denker, J. S., Gardner, W. R., Graf, H. P., Henderson, D., Howard, R. E., Hubbard, W., Jackel, L. D., Baird, H. S., & Guyon, I. (1988) · Cited by 158
Hybrid $k$ -Nearest Neighbor Classifier
Yu, Z., Chen, H., Liuxs, J., You, J., LEUNG, H. K. N., & Han, G. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2443857 · Cited by 133
Hybrid Adaptive Classifier Ensemble
Yu, Z., Li, L., Liu, J., & Han, G. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2322195 · Cited by 110
Feasibility of random basis function approximators for modeling and control
Tyukin, I., & Prokhorov, D. V. (2009) · doi:10.1109/cca.2009.5281061 · Cited by 95 · cited 1×
“Therefore, RVFLNN has been employed to solve problems in diverse domains, including the context of modeling and control [25].”
MethodFeng, S., & Chen, C. L. P. (2016) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2016.2639064 · Cited by 84 · cited 3×
“The one-layer FRBM and our proposed broad learning results are tested on a 3.40-GHz Intel i7-6700 CPU processor PC with MATLAB platform.”
BackgroundResultInfluentialSelf-citationAdaptive Method for Nonsmooth Nonnegative Matrix Factorization
Yang, Z., Xiang, Y., Xie, K., & Lai, Y. S. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2517096 · Cited by 70 · cited 1×
“Among the various algorithms, the singular value decomposition (SVD) and nonnegative matrix factorization (NMF) [35] are widely used for exploratory data analysis.”
MethodQuickly Generating Representative Samples from an RBM-Derived Process
Breuleux, O., Bengio, Y., & Vincent, P. (2011) · Neural Computation · doi:10.1162/neco_a_00158 · Cited by 67 · cited 1×
“MNIST data set [51].”
MRM-Lasso: A Sparse Multiview Feature Selection Method via Low-Rank Analysis
Yang, W., Gao, Y., Shi, Y., & Cao, L. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2396937 · Cited by 65 · cited 1×
“Specifically, sparse feature learning models have been attractive that could explore essential characterization [12], [42], [43].”
Background
Research works printed but not linked: 2
- serre, 2002, Matrices, Theory and Applications
- goodfellow, 2016, Deep Learning
Cited by
Chen, X., Zhang, H., Wu, C., Mao, S., Ji, Y., & Bennis, M. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2876279 · Cited by 680
Universal Approximation Capability of Broad Learning System and Its Structural Variations
Chen, C. L. P., Liu, Z., & Feng, S. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2866622 · Cited by 549
“Hence, only the increment of the additional enhancement nodes is available here, and the algorithm is similar to the corresponding section of the original BLS in [3].”
BackgroundMethodInfluentialSelf-citationChen, H., Jiang, B., Ding, S. X., & Huang, B. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3029946 · Cited by 521
Fuzzy Broad Learning System: A Novel Neuro-Fuzzy Model for Regression and Classification
Feng, S., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2857815 · Cited by 490
“BLS [28] is an improved flat framework [29] which inherits the major feature and superiority of a random vector functional-link NN [30].”
BackgroundSelf-citationA Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains
Chen, H., & Jiang, B. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2897583 · Cited by 413
“1: Preprocess Zς based on step 1 in Algorithm 1 as Zς ; 2: Project Zς into obtained principal and residual subspaces in step 2 in Algorithm 1 as T̂ς and T̃ς ; 3: Define Tς = [T̂ς T̃ς ] as the mapped feature nodes of Zς ; 4: Obtain the enhancement nodes Hς of Zς [126]; 5: Output the ς -th type of fault features ς based…”
Method
Metadata
- Authors
- Chen, C. L. P., & Liu, Z.
- Affiliations
- Chinese Academy of Sciences (CN)
- University of Macau (MO)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2018-01
- Volume
- 29
- Issue
- 1
- Pages
- 10-24
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2738226240
- Cited by
- 1,957
- References
- 58
- Citations by year
- 2026: 177 · 2025: 312 · 2024: 303 · 2023: 255 · 2022: 270 · 2021: 223 · 2020: 177 · 2019: 158 · 2018: 73
- FWCI
- 68.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Fundo para o Desenvolvimento das Ciências e da Tecnologia (019/2015/A1)
- UM Research Grants
- National Nature Science Foundation of China (61572540)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- broad learning system, incremental learning, flat network architecture, network expansion, model reduction, singular value decomposition, object recognition
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.
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.