A No-Reference Objective Image Sharpness Metric Based on the Notion of Just Noticeable Blur (JNB)
The DOI matches its Crossref record; 24 of the 25 references it cites were found in a registry or an index.
Abstract
This work presents a perceptual-based no-reference objective image sharpness/blurriness metric by integrating the concept of just noticeable blur into a probability summation model. Unlike existing objective no-reference image sharpness/blurriness metrics, the proposed metric is able to predict the relative amount of blurriness in images with different content. Results are provided to illustrate the performance of the proposed perceptual-based sharpness metric. These results show that the proposed sharpness metric correlates well with the perceived sharpness being able to predict with high accuracy the relative amount of blurriness in images with different content.
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
“Earlier NR-IQA methods used natural scene statistics, sharpness, blur, gradient profiles, and transform domain statistics to capture perceptually meaningful degradation without requiring a pristine reference [55-58].”
From A Survey and Tutorial on Image Quality Assessment with a Contrast-Weighted Structural Similarity Framework (2026) · cites this paper as [58]
Citations
Cites
Live image quality assessment database release 2
Sheikh, H. R. (2005) · Medical Entomology and Zoology · Cited by 1,275
Signal compression based on models of human perception
Jayant, N., Johnston, J., & Safranek, R. (1993) · Proceedings of the IEEE · doi:10.1109/5.241504 · Cited by 796 · cited 4×
“By definition , the JND is the minimum amount by which a stimulus intensity must be changed relative to a background intensity in order to produce a noticeable variation in sensory experience.”
BackgroundInfluentialProbability summation and regional variation in contrast sensitivity across the visual field
Robson, J. G., & Graham, N. (1981) · Vision Research · doi:10.1016/0042-6989(81)90169-3 · Cited by 616 · cited 1×
“…as the JNB. Knowing that the HVS tolerance is subject-dependent , subjective testing is performed and the JNBs are determined in function of the local contrast and are used to derive an edge-based sharpness metric based on a HVS model that makes use of probability summation over space [4].”
MethodDigital video and HDTV algorithms and interfaces
(2003) · Choice Reviews Online · doi:10.5860/choice.40-6437 · Cited by 545
Perceptual blur and ringing metrics: application to JPEG2000
Marziliano, P., Dufaux, F., Winkler, S., & Ebrahimi, T. (2004) · Signal Processing: Image Communication · doi:10.1016/j.image.2003.08.003 · Cited by 491 · cited 9×
“Note that the sharpness metric of [7] is also referred to as the perceptual blur metric in the literature but it does not incorporate HVS-based perceptual weighting.”
BackgroundMethodInfluentialRussek, E., & Hays, W. L. (1982) · Journal of the American Statistical Association · doi:10.2307/2287811 · Cited by 460
Objective video quality assessment
(2003) · Handbook of Video Databases · doi:10.1201/9780203489864-45 · Cited by 359 · cited 1×
“These methods are useful in various image/video processing applications, such as compression , communication, printing, display, analysis, registration, restoration, and enhancement [1].”
MethodComparison of autofocus methods for automated microscopy
Firestone, L., Cook, K., Culp, K., Talsania, N., & Preston, K. (1991) · Cytometry · doi:10.1002/cyto.990120302 · Cited by 348 · cited 1×
“• Frequency threshold metric [8]: Based on computing the summation of all frequency component magnitudes above a certain threshold .”
BackgroundPractical issues in pixel-based autofocusing for machine vision
Ng Kuang Chern, N., Neow, P. A., & Ang, M. H. (2002) · Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164) · doi:10.1109/robot.2001.933045 · Cited by 199 · cited 1×
“• Histogram entropy-based metric [11]: The entropy is a measure of the information content of an image; if the probability of occurrence of each gray level is low, the entropy is high and vice versa.”
BackgroundBlur determination in the compressed domain using DCT information
Marichal, X., Ma, W.-Y., & Zhang, H. (1999) · Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348) · doi:10.1109/icip.1999.822923 · Cited by 195 · cited 1×
“• Histogram frequency-based metric [12]: The metric proposed by Marichal et al. is based on the occurrence histogram of nonzero DCT coefficients throughout all 8 8 blocks of the image (more weight is given to DCT coefficients on the diagonal).”
Research works printed but not linked: 6
- 1998, Methodology for the Subjective Assessment of the Quality of Television Pictures
- freedman, 1997, Statistics
- batten, 2000, Autofocusing and Astigmatism Correction in the Scanning Electron Microscope
- zhang, 2003, a kurtosis-based statistitcal measure for two-dimensional processes and its application to image sharpness, Proc Section of Physical and Engineering Sciences of American Statistical Society, 4730
- wang, 2003, The Handbook of Video Databases Design and Applications (B Furht and O Marqure), 1041
- sheikh, 2003, LIVE Image Quality Assessment Database
Cited by
Items 701–775 of 775
Document Image Blur Estimation with Multiresolution Toggle Mapping
Yafenz, L., & Ying, L. (2019) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai48974.2019.9010331
Kiruthika, S. U., & Masilamani, V. (2019) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict48419.2019.9066166
“SROCC PLCC RMSE LIVE CSIQ TID2013 LIVE CSIQ TID2013 LIVE CSIQ TID2013 JNB [7] 0.”
MethodComparative Study of Classifiers for Blurred Images
Gueraichi, R., & Serir, A. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-52246-9_23
Adaptive fusion of bright-field microscopy images acquired in different focal planes
Catanante, V. A. A. (2020) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.55.2020.tde-10092020-164245
“The parameters σJNB and β are chosen by means of a least-square fitting to approximate the probabilities P with the answers from volunteers.”
MethodInfluentialA Framework for 3D Reconstruction Dataset Preprocessing
Wang, X., Luo, X., Yu, M., Shi, C., Zhu, Y., & Chen, G. (2019) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv47840.2019.00059
On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild
Matta, R. R. (2017) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.6178
“compression [24], JPEG-2K and JPEG compression [25], blur [26] and, blurred and JPEG-2k compression [27].”
Automated Real-time 3D Visual Servoing Control of Single Cell Surgery Processes
Yao, B., & Mills, J. K. (2021) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma52036.2021.9512683
Sharpness Enhancement of Stereo Images Using a Depth-Based Per-Pixel Regularization
Andrade, J. (2021) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa52424.2021.9555517
Full-reference Image Quality Metric For Computer-rendered Stereoscopic Images
Li, L., & Chen, C. (2021) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs53707.2021.9587950
Anjankar, S., Pund, A. M., & Jawarkar, P. (2021) · INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING · doi:10.47164/ijngc.v12i5.440
Maître, H. (2015) · Wiley eBooks · doi:10.1002/9781119238447.biblio
Xu, L., Lin, W., & Kuo, C. ‐. J. (2015) · Springer briefs in electrical and computer engineering · doi:10.1007/978-981-287-468-9_1
Blind image quality assessment based on Multi-resolution Local Structures
Khorashadizadeh, S. M., SadeghiBakhi, M., Seifishahpar, F., & Latif, A. (2021) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke54056.2021.9721506
“Blur detection’s probability is measured by the approach provided by [16].”
MethodA reference-free image quality assessment method based on saliency regions
Xu, C., Zang, J., & Zhang, S. (2022) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1117/12.2636924
No-reference image blurriness assessment using divisive normalization
Dey, R., & Bhattacharjee, D. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02179-2
“Table 3 Comparison with existing methods Database Metric JNB [4] CPBD [5] BIBLE [21] Wavelet-based [22] NIBEM (proposed)”
Method(2011) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt.2011.808
Deep Learning for Image/Video Restoration and Super-resolution
Tekalp, A. M. (2022) · doi:10.1561/9781680839739
A Brief Review of Image Quality Assessment Techniques for Laparoscopic Image Restoration
Xiangwei Qin1, 2. (2022) · International Journal of Frontiers in Medicine · doi:10.25236/ijfm.2022.040101
“The JNB is the minimum value corresponding to the perceived blurring of the local edges of the image, provided that it is higher than the JND contrast.”
BackgroundInfluentialSimulating Visual Mechanisms by Sequential Spatial-Channel Attention for Image Quality Assessment
You, J., & Korhonen, J. (2022) · Workshop on Quality of Experience in Visual Multimedia Applications (QoEVMA) · doi:10.1145/3552469.3555714
“Traditional work on NR-IQA models mainly targets at images with certain distortion types, e.g., compression and transmission artifacts [1][2].”
BackgroundMethodDataset for assessing the definition of underwater images
Wang, D., Zhang, Z., Yang, X., & Sun, Z. (2022) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca56264.2022.9987963
“Content BIQME[21] Contrast, Blur, Brightness, Color BISHARP[22] Sharpness/blur JNB[23] Sharpness/blur UCIQE[4] Hue, Contrast and Saturation UIQM[5] Color, sharpness and contrast CCF[6] Color, Contrast and Blur The results obtained by the algorithm (using UCIQE as an example here) are shown in Fig.”
MethodVideo metric measurements in an FPGA for use in objective no-reference video quality analysis
Nordeng, E. T. (2013) · BIBSYS Brage (BIBSYS (Norway))
Chen, A. W., & Loew, M. H. (2023) · Journal of medical imaging · doi:10.1117/1.jmi.10.s1.s11920
Wavelet Transform Domain for Deep Image Compression Using High Frequency Sub-Band Prediction
Garg, U. (2019) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.17762/turcomat.v10i1.13556
Heart rate measurement and blur image quality metric via image processing: An overview
Paramesran, R., & Hassan, M. F. (2023) · AIP conference proceedings · doi:10.1063/5.0140251
A Study on the Multi-focus Method of Microscopic Images for Oilpainting Analysis
Kim, H., Lee, D.-Y., Choi, D., Kang, J., & Lee, D.-W. (2023) · Journal of the Korean Society for Precision Engineering · doi:10.7736/jkspe.022.151
“영상 품질 평가 관련 연 구에서 초점 지수와 영상 품질을 공유하여 측정할 수 있는 지수 를 적용하였다[23,24].”
The Role of Background Blur and Contrast in Perceived Translucency of See-through Filters
Mivehforoushi, A. A., Gigilashvili, D., & Hardeberg, J. Y. (2023) · London Imaging Meeting · doi:10.2352/lim.2023.4.1.15
An Efficient Approach of Assessing Quality of Blurred Image
Baig, M. A., Moinuddin, A. A., Khan, E., & Ghanbari, M. (2023) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001423540186
Hybrid Reduced-Reference Video Quality Assessment of Streaming Services Over Reliable Transport
Lee, C., Youn, J., & Woo, S. (2023) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa59645.2023.10345928
No-Reference Image Sharpness Assessment Based on Perceptually-Weighted Image Gradients
Andrade, J. (2023) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa59645.2023.10345886
“Narvekar et al. [28] proposed an improvement to [27] which exploits the fact that blur below the JNB threshold is unlikely to be perceived.”
BackgroundMethodInfluentialWang, M., Zhang, R., Huang, L., & Li, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i9.28884
“3) BS is measured with the difference be-tween the original and blurred images with the maximum standard deviation (Ferzli and Karam 2009).”
MethodThe Inter-Relationship Between Photographic Aesthetics and Technical Quality
Götz-Hahn, F., Wong, L.-K., & Hosu, V. (2023) · Springer eBooks · doi:10.1007/978-3-031-50269-9_14
Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Peng, B., Liu, M., Zhang, Z., Xu, K., & Li, D. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2092-7_3
No-Reference Image Sharpness Assessment via Multi-scale Texture Naturalness
Sun, Z., Hua, G., & Xu, Y. (2023) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca59734.2023.00165
“In an early study, the Sobel operator was first introduced to detect image edges and the average edge width was calculated as the final sharpness score [6].”
MethodAbbott, T. B., & Yuan, F. (2024) · Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation · doi:10.1117/12.3010943
“Thus, MSC is more sensitive to irregularities due to damage-induced stiffness reduction than the mode shapes itself [19], [20], [21], [22] since the curvature value will increase around the damage region with reduced stiffness.”
BackgroundNo-reference image sharpness assessment via elastic net based mid-level feature selection
Yu, S., Cheng, H. B., Wang, J., Jin, M., & Zhu, B. (2024) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1145/3670105.3670162
“Blurriness is found to distort the local contrast, and the concept of Just Noticeable Blur (JNB) is designed and embedded into a probability summation framework [6] and into the Cumulative Probability of Blur Detection (CPBD) [24].”
InfluentialYang, C., Tai, Z., Gu, X., & Wang, K. (2024) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss53475.2024.10641352
“Researchers at Arizona State University proposed a method of using the edge width of image motion direction as a measure of motion blur [6, 7], which has been widely studied and applied.”
MethodNeural Network Method for Detecting Blur in Histological Images
Nazarenko, G. S., & Krylov, A. S. (2024) · Программирование · doi:10.31857/s0132347424030075
DCT-Based No-Reference Quality Assessment of AWGN Images
Baig, M. A., Moinuddin, A. A., & Khan, E. (2025) · SN Computer Science · doi:10.1007/s42979-025-03749-0
“On the other hand, distortion-specific algorithms are specifically tuned for known distortion types, resulting in simpler and highly accurate methods [19–31].”
No-Reference Image Quality Assessment Method Based on Mutual Information of Regions
Yuan, Z. J., Wang, P., Li, J., Li, Y., & Xia, M. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-5318-8_6
Enhancing In-Cabin Video Experience Using Driver Monitoring IR CameraPreprint
HAMMAD, M. S., & Al‐Atabany, W. (2025) · Research Square · doi:10.21203/rs.3.rs-7059997/v1
Algorithmic Research of Image Blur Detection
Yuan, Y., Liu, H., Liu, H., & Fu, H. C. (2025) · IEEE International Conference on Energy and Electrical Engineering (EEE) · doi:10.1109/eee64897.2025.11162896
“Reference [9], reference [10], reference [11] and reference [6] proposed different methods for detecting image blur, serving as comparison methods for this experiment.”
Variance-Driven U-Net Weighted Training and Chroma-Scale-Based Multi-Exposure Image Fusion
Son, C.-W., Go, Y.-H., Lee, S.-H., & Lee, S.-H. (2025) · Mathematics · doi:10.3390/math13223629
Gabhane, Y. S., Jain, T. K., & Kamble, V. M. (2025) · Journal of Modern Optics · doi:10.1080/09500340.2025.2599956
“Previous studies on NR-IQA mainly looked at quality characteristics linked to particular types of distortion, like blocking artifacts [18], sharpness [19], and image blurring.”
Brüggemann, M., Erdler, O., Kays, R., & Springer, P. (2013) · Technische Universität Dortmund Eldorado (Technische Universität Dortmund) · doi:10.17877/de290r-5260
“[2] and [3]) or analyze t he sharpness in the spectral domain (e.”
BackgroundMachine Vision for Improved Human-Robot Cooperation in Adverse Underwater ConditionsPreprint
Islam, M. J. (2019) · arXiv (Cornell University) · doi:10.13140/rg.2.2.11800.93446
Generalized Quantitative Evaluation in Broadband Diffractive Imaging
Chen, C., Zhou, Y., Wang, Y., Xia, H., & Chang, S. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3655894
“DWE is compared with several commonly used evaluation functions, including three feature-domain methods (DIF [27], GRA [28], AMP [26]), one Fourier-domain mean squared error (mse) method widely adopted in CDI, and two NRIQ metrics (JNB [35], bR [36]).”
Dargel, A., Troschitz, J., Gude, Μ., & Kupfer, R. (2026) · e-Journal of Nondestructive Testing · doi:10.58286/32601
An Image-Quality Assessment Algorithm for Solar Tone-Mapped Images Based on Visual Simulation
Bian, Q., & Rao, C. (2026) · Applied Sciences · doi:10.3390/app16041811
Efficient Sensor Utilization and Advanced Elastogram Image Generation Methods in Ultrasound Imaging
Konda, S., & Chaoui, H. (2026) · IEEE Access · doi:10.1109/access.2026.3664675
“In our work, we calculated local variance [32] and histogram width [33] based sharpness metrics.”
Region-guided preprocessing and U-Net variants for improved panoramic dental radiograph segmentation
Sogur, N., & Kazak, N. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110068
Development of a portable gamma camera for accurate 3-D localization of radioactive hotspots
Paradiso, V. (2017) · theses.fr (ABES) · doi:10.70675/f2823a73z565fz4c4ez8d14zf9754f9320ef
Multi-modality quality assessment for unconstrained biometric samples
Liu, X. (2018) · theses.fr (ABES) · doi:10.70675/e4eba9ccz364dz4e63z9714zff4409cb860c
“[122] present a perceptually-based no-reference image sharpness metric by integrating the concept of just noticeable blur into a probability summation model.”
BackgroundQuality assessment of stereoscopic 3D content based on binocular perception
Fan, Y. (2019) · theses.fr (ABES) · doi:10.70675/c06f8c6fzd28bz433cza7e2z03f88a6cb9cb
Tatouage des images médicales partagées
Karasad, M. (2018) · theses.fr (ABES) · doi:10.70675/42584764za3fez47ebzb908z2669f5116d39
Faula, Y. (2020) · theses.fr (ABES) · doi:10.70675/bffd488az2ca0z484ezb6cfz5c45dd3b9fb1 · Cited by 1
évaluation et correction du flou respiratoire en médecine nucléaire sans matériel externe
Morland, D. (2020) · theses.fr (ABES) · doi:10.70675/282c4af7z5ff4z4c02z8c63z83560a58ab1f
Quality Evaluation of Contrast-Enhanced Images: Central Asian Perspectives
Kadyrova, A., & Pedersen, M. (2026) · Journal of Imaging Science and Technology · doi:10.2352/j.imagingsci.technol.2026.70.2.020403
An affordable fiducial marker strategy for reliable autofocus in long‐term live microscopy
Djafer-Cherif, I., & Waclaw, B. (2026) · Journal of Microscopy · doi:10.1111/jmi.70127
“11 However, most of these methods assume that the sample contains sufficient structural features for the sharpness metric to exhibit a clear, rapidly decaying peak away from the focal plane–in other words, a well-defined local maximum.”
Zhang, Z., Chen, K., Yang, C., Zhang, X., & Wang, Z. (2026) · Remote Sensing · doi:10.3390/rs18122039
“In addition, no-reference blur or sharpness assessment methods often use gradient, wavelet-, edge, or frequency-related cues to measure structural degradation, indicating that high-frequency and directional components are closely associated with image clarity and boundary preservation [50,51].”
Wang, Y., Fang, J., Zhang, X., Wang, X. Z., Liu, X., & Li, P. (2026) · Sensors · doi:10.3390/s26134097
FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
Hoang, M. S., Tran, D. P., Đức, Q. N., Phuong, D. H., & Kim, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37271-0_8
Multi-Level Feature Fusion for Image Blur Assessment: An Adaptive Machine Learning Approach
Bohra, S., Rani, M., & Choudhary, R. R. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.424
Bohra, S., Rani, M., Choudhary, R. R., & Kumar, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7078352
Visual fidelity–driven quality assessment of medical image translation
Bizjak, Ž., Zagar, J., & Špiclin, Ž. (2026) · Scientific Reports · doi:10.1038/s41598-026-60570-2
Aminfar, K., & Lattanzi, D. (2026) · Data-Centric Engineering · doi:10.1017/dce.2026.10070
“…2021; Zhu et al., 2023), include the Variance of Laplacian, a second-order derivative metric, acting as a high pass filter (Tai and Yang, 2008; Bansal et al., 2016) that evaluates image sharpness by measuring intensity variance, where higher values indicate sharper images (Ferzli and Karam, 2009).”
Abay, S. G., Asmare, M. H., Jacob, J. A., & Geurts, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38091-3_13
Mathematical Models for Quality Analysis of Mobile Video
Zhao, S.-Q., Jiang, H., Liang, C., Sherif, S., & Tarraf, A. (2016) · International Journal of Numerical Analysis and Modeling · doi:10.4208/ijnam.v13.n6.p879
“However, as in [6] and [14], we also find that such processing does not help improve accuracy of blur estimation, on the contrary, it will increase the computational complexity.”
Sogur, N. (2025) · Bilecik Şeyh Edebali University Institutional Repository
Metadata
- Authors
- Ferzli, R., & Karam, L. J.
- Affiliations
- Arizona State University (US)
- ORCID
- Karam, L.J.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2009-04
- Volume
- 18
- Issue
- 4
- Pages
- 717-728
- ISSN
- 1057-7149 (ISSN-L)
- OpenAlex
- W2138088051
- Cited by
- 758
- References
- 25
- Citations by year
- 2026: 11 · 2025: 18 · 2024: 28 · 2023: 42 · 2022: 32 · 2021: 38 · 2020: 47 · 2019: 48 · 2018: 56 · 2017: 73 · 2016: 86 · 2015: 61 · 2014: 69 · 2013: 48 · 2012: 40
- FWCI
- 37.16
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- image sharpness, blurriness, no-reference image quality assessment, perceptual image quality
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.