Multi-task Learning Using Multi-modal Encoder-Decoder Networks with Shared Skip Connections
Abstract
Multi-task learning is a promising approach for efficiently and effectively addressing multiple mutually related recognition tasks. Many scene understanding tasks such as semantic segmentation and depth prediction can be framed as cross-modal encoding/decoding, and hence most of the prior work used multi-modal datasets for multi-task learning. However, the inter-modal commonalities, such as one across image, depth, and semantic labels, have not been fully exploited. We propose a multi-modal encoder-decoder networks to harness the multi-modal nature of multi-task scene recognition. In addition to the shared latent representation among encoder-decoder pairs, our model also has shared skip connections from different encoders. By combining these two representation sharing mechanisms, the proposed method efficiently learns a shared feature representation among all modalities in the training data. Experiments using two public datasets shows the advantage of our method over baseline methods that are based on encoder-decoder networks and multi-modal auto-encoders.
Integrity signals
Registry
Cites
Statistics
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?
GNN-based methods model multimodal data through graph structures, enhancing global and robust semantic understanding.
“GNN-based methods [52,53] model multimodal data through graph structures, enhancing global and robust semantic understanding.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [53]
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · see citing works
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · see citing works
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · see citing works
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · see citing works
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760 · see citing works
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Cipolla, R., Gal, Y., & Kendall, A. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00781 · Cited by 3,657 · see citing works
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, D., Puhrsch, C., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1406.2283 · Cited by 3,442 · see citing works
Eigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862 · see citing works
(2011) · Cited by 2,752 · see citing works
An Image Inpainting Technique Based on the Fast Marching Method
Telea, A. (2004) · Journal of Graphics Tools · doi:10.1080/10867651.2004.10487596 · Cited by 1,421 · see citing works
Multimodal Learning with Deep Boltzmann Machines
Srivastava, N., & Salakhutdinov, R. (2012) · doi:10.5555/2627435.2697059 · Cited by 1,070 · see citing works
Multimodal Distributional Semantics
Bruni, E., Tran, N. K., & Baroni, M. (2014) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4135 · Cited by 910 · see citing works
Deep convolutional neural fields for depth estimation from a single image
Liu, F., Shen, C., & Lin, G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299152 · Cited by 892 · see citing works
MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Teichmann, M., Weber, M., Zollner, M., Cipolla, R., & Urtasun, R. (2018) · 2018 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2018.8500504 · Cited by 681 · see citing works
Multimodal deep learning for robust RGB-D object recognition
Eitel, A., Springenberg, J. T., Spinello, L., Riedmiller, M., & Burgard, W. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353446 · Cited by 647 · see citing works
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
Li, X., Zhao, L.-M., Wei, L., Yang, M., Wu, F. Q., Zhuang, Y., Ling, H., & Wang, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2579306 · Cited by 535 · see citing works
Integrated Imaging and Vision Techniques for Industrial Inspection
Liu, Z., Ukida, H., Ramuhalli, P., & Niel, K. S. (2015) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-6741-9 · Cited by 270 · see citing works
Dense 3D semantic mapping of indoor scenes from RGB-D images
Hermans, A., Floros, G., & Leibe, B. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907236 · Cited by 258 · see citing works
Deep Multi-task Representation Learning: A Tensor Factorisation ApproachPreprint
Yang, Y., & Hospedales, T. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.06391 · Cited by 202 · see citing works
MultiNet: Real-time Joint Semantic Reasoning for Autonomous DrivingPreprint
Teichmann, M., Weber, M., Zöllner, M., Cipolla, R., & Urtasun, R. (2016) · arXiv (Cornell University) · doi:10.17863/cam.26778 · Cited by 164 · see citing works
Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling
Uhrig, J., Cordts, M., Franke, U., & Brox, T. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45886-1_2 · Cited by 154 · see citing works
Towards multimodal deep learning for activity recognition on mobile devices
Radu, V., Lane, N. D., Bhattacharya, S., Mascolo, C., Marina, M. K., & Kawsar, F. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct · doi:10.1145/2968219.2971461 · Cited by 147 · see citing works
Improved Multimodal Deep Learning with Variation of Information
Sohn, K., Shang, W., & Lee, H. (2014) · neural information processing systems · Cited by 142 · see citing works
Liao, Y., Kodagoda, S., Wang, Y., Shi, L., & Liu, Y. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487381 · Cited by 109 · see citing works
Multi-modal Auto-Encoders as Joint Estimators for Robotics Scene Understanding
Cadena, C., Dick, A., & D. Reid, I. (2016) · Robotics: Science and Systems XII · doi:10.15607/rss.2016.xii.041 · Cited by 93 · see citing works
Facial Attributes Classification Using Multi-task Representation Learning
Ehrlich, M., Shields, T. J., Almaev, T. R., & Amer, M. R. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.99 · Cited by 93 · see citing works
Imagined Visual Representations as Multimodal Embeddings
Collell, G., Zhang, T., & Moens, M. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11155 · Cited by 81 · see citing works
Multi-modal Unsupervised Feature Learning for RGB-D Scene Labeling
Wang, A., Lu, J., Wang, G., Cai, J., & Cham, T.-J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_30 · Cited by 50 · see citing works
Visually Grounded Meaning Representations
Silberer, C., Ferrari, V., & Lapata, M. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2635138 · Cited by 46 · see citing works
Attributes for Improved Attributes: A Multi-Task Network for Attribute ClassificationPreprint
Hand, E., & Chellappa, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.07360 · Cited by 25 · see citing works
Multi-modal Variational Encoder-Decoders
Serban, I. V., Ororbia, A. G., Pineau, J., & Courville, A. C. (2017) · Cited by 10 · see citing works
Flagged first, then by citations
1 of the 33 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Xu, D., Ouyang, W., Wang, X., & Sebe, N. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00077 · Cited by 541 · see citing works
Zhao, F., Zhang, C., & Geng, B. (2024) · ACM Computing Surveys · doi:10.1145/3649447 · Cited by 480 · see citing works
Multi-modal learning from unpaired images: application to multi-organ segmentation in CT and MRI
Valindria, V. V., Pawlowski, N., Rajchl, M., Lavdas, I., Aboagye, E. O., Rockall, A. G., Rueckert, D., & Glocker, B. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00066 · Cited by 146 · see citing works
“Inspired by one of the architectures in bi-modal deep AE [20] and multi-modal encoder-decoder networks in [14], we use dual-stream in both encoder and decoder.”
BackgroundMethodA deep learning approach for the transonic flow field predictions around airfoils
Duru, C., Alemdar, H. O., & Baran, Ö. U. (2022) · Computers & Fluids · doi:10.1016/j.compfluid.2022.105312 · Cited by 107 · see citing works
Fayad, I., Ciais, P., Schwartz, M., Wigneron, J., Baghdadi, N. N., Truchis, A. D., d’Aspremont, A., Frappart, F., Saatchi, S. S., Sean, E., et al. (2023) · Remote Sensing of Environment · doi:10.1016/j.rse.2023.113945 · Cited by 93 · see citing works
“By having separate encoders, the network can learn to extract relevant features and representations independently for each modality, rather than trying to extract common features for all modalities (Kuga et al., 2017).”
Unified generative adversarial networks for multimodal segmentation from unpaired 3D medical images
Yuan, W., Wei, J., Wang, J., Ma, Q., & Taşdizen, T. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101731 · Cited by 42 · see citing works
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“Traditional multimodal fusion methods offer a basic theoretical framework but struggle with complex data.”
Sedghi, A., Mehrtash, A., Jamzad, A., Amalou, A., Wells, W. M., Kapur, T., Kwak, J. T., Türkbey, B., Choyke, P. L., Pinto, P. A., et al. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02172-5 · Cited by 39 · see citing works
“[13] proposed a multimodal, multitask encoder– decoder network with shared latent and skip connection for simultaneous learning from RGB and depth images.”
BackgroundMethodMix and Match Networks: Encoder-Decoder Alignment for Zero-Pair Image Translation
Wang, Y., van de Weijer, J., & Herranz, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00573 · Cited by 32 · see citing works
High-quality PET image synthesis from ultra-low-dose PET/MRI using bi-task deep learning
Sun, H., Jiang, Y., Yuan, J., Wang, H., Liang, D., Fan, W., Hu, Z., & Zhang, N. (2022) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-116 · Cited by 23 · see citing works
“The basic bi-task structure was inspired by the work of Kuga et al. (38), with some changes made according to our application.”
InfluentialMarinov, Z., Reiß, S., Kersting, D., Kleesiek, J., & Stiefelhagen, R. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00242 · Cited by 19 · see citing works
“[14] provide a summary of existing fission methods, noting that all previous methods either use a joint encoder before the fission into individual decoders [27, 44, 1, 31] or share skip connections [25].”
MethodYuan, W., Wei, J., Wang, J., Ma, Q., & Taşdizen, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32248-9_26 · Cited by 19 · see citing works
Vu, M. T., & Jardani, A. (2022) · Journal of Hydrology · doi:10.1016/j.jhydrol.2022.128167 · Cited by 16 · see citing works
Deep Learning for Multimodal Data Fusion
Kanezaki, A., Kuga, R., Sugano, Y., & Matsushita, Y. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-817358-9.00008-1 · Cited by 15 · see citing works
Self-citationArmitage, J., Kacupaj, E., Tahmasebzadeh, G., Swati, Maleshkova, M., Ewerth, R., & Lehmann, J. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3412783 · Cited by 13 · see citing works
“Multitask learning systems that learn on multimodal data are also an active area of research in relation to multimodal representation learning, location estimation, and scene understanding [5, 28].”
BackgroundYang, M., Yang, S., & Wong, W. E. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3421591 · Cited by 11 · see citing works
“Meanwhile, some studies found that the widely used encoder-decoder structure with separate encoders for each feature subset has the risk of insuf fi cient data utilization and inclusion of redundant parameters [45], [46].”
ResultPlanche, B., Zakharov, S., Wu, Z., Hutter, A., Harald Kosch, A., & Ilić, S. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967829 · Cited by 11 · see citing works
“We thus consolidate several state-of-the-art works [1], [2], [3], [4] to develop a custom generator with multiple convolutional decoders—one for each relevant synthetic modality (e.”
InfluentialCOMPASS: Contrastive Multimodal Pretraining for Autonomous Systems
Ma, S., Vemprala, S. H., Wang, W., Gupta, J. K., Song, Y., McDufft, D., & Kapoor, A. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9982241 · Cited by 11 · see citing works
“A natural extension of multimodal learning algorithms has been applied to the multi-task learning setting [28], [29], [30].”
MethodDriven by Vision: Learning Navigation by Visual Localization and Trajectory Prediction
Leordeanu, M., & Paraicu, I. (2021) · Sensors · doi:10.3390/s21030852 · Cited by 10 · see citing works
“In the literature, there are models [1,2] that use visual information to extract highlevel semantics of the traffic scene and decide the steering action conditioned on these representations.”
MethodMultichannel Semantic Segmentation with Unsupervised Domain Adaptation
Watanabe, K., Saito, K., Ushiku, Y., & Harada, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_37 · Cited by 9 · see citing works
Mix and Match Networks: Cross-Modal Alignment for Zero-Pair Image-to-Image Translation
Wang, Y., Herranz, L., & van de Weijer, J. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01340-z · Cited by 9 · see citing works
“Training a multi-task multimodal encoder–decoder network was recently studied by Kuga et al. (2017).”
BackgroundTranscoding across 3D shape representations for unsupervised learning of 3D shape feature
Furuya, T., & Ohbuchi, R. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.07.012 · Cited by 8 · see citing works
“[34] proposed crossprediction of color and depth of RGB-D images to obtain image features useful for semantic segmentation of RGB-D images.”
BackgroundHeuristic Depth Estimation with Progressive Depth Reconstruction and Confidence-Aware Loss
Zhang, J., Li, L., Yan, C. C., Sun, Y., Shen, T., Zhang, J., & Wang, Z. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475386 · Cited by 6 · see citing works
“Researchers try to solve this problem by introducing different training strategies, such as multi-task learning [12, 29, 63], semi-supervised learning with photometric loss [1, 18, 27], etc.”
BackgroundActive Learning with Task Consistency and Diversity in Multi-Task Networks
Hekimoglu, A., Schmidt, M., & Marcos-Ramiro, A. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00249 · Cited by 5 · see citing works
“Multi-task networks have demonstrated state-of-the-art (SOTA) performance across a range of vision tasks, including semantic segmentation [3,33] and monocular depth estimation [16, 22].”
BackgroundSharing Decoders: Network Fission for Multi-task Pixel Prediction
Hickson, S., Raveendran, K., & Essa, I. A. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00371 · Cited by 5 · see citing works
“al [21] use several different modalities as both inputs and outputs with each having it’s own encoder and decoder but sharing skip connections and a shared latent representation.”
BackgroundTimber Tracing with Multimodal Encoder-Decoder Networks
Zolotarev, F., Eerola, T., Lensu, L. T., Kalviainen, H. A., Haario, H., Heikkinen, J., & Kauppi, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29891-3_30 · Cited by 5 · see citing works
“For example, in [6], U-Net is used as the encoder-decoder to translate data to different modalities.”
MethodSpatio-Temporal Consistency and Negative Label Transfer for 3D Freehand US Segmentation
Duque, V. G., Chanti, D. A., Crouzier, M., Nordez, A., Lacourpaille, L., & Mateus, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59710-8_69 · Cited by 5 · see citing works
“Multi-task learning [11, 8] shown to improve the performance of different tasks with auxiliary objective functions.”
BackgroundLi, X., Sayer, A. M., Carroll, I. T., Huang, X., & Wang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70381-2_1 · Cited by 4 · see citing works
Cross-Modal Supervision Based Road Segmentation and Trajectory Prediction With Automotive Radar
Wang, Z., Jin, Y., Deligiannis, A., Fuentes-Michel, J.-C., & Vossiek, M. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3440093 · Cited by 3 · see citing works
Zhang, Y., Kers, J., Cassol, C. A., Roelofs, J. J. T. H., Idrees, N., Farber, A. M., Haroon, S. A., Daly, K. P., Ganguli, S., Chitalia, V. C., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.04658 · Cited by 3 · see citing works
“For example, Kuga and colleagues performed multi-task learning by combining multimodal data with a shared latent representation between multiple encoder-Zhang decoder networks [9].”
MethodXi, Y., Lu, T., Lu, J., Kang, X., & Shutao Li, A. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3670458 · Cited by 2 · see citing works
“1, the existing solutions are mainly categorized into three paradigms: modality reconstruction [5], [6], [7], multi-task learning [8], [9], [10], and knowledge distillation [11], [12], [13].”
Split-AE: An Autoencoder-based Disentanglement Framework for 3D Shape-to-shape Feature Transfer
Saha, S., Minku, L. L., Yao, X., Sendhoff, B., & Menzel, S. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892814 · Cited by 2 · see citing works
“Research on training autoencoder-based architectures for multiple tasks [9] relies on a combination of geometric loss and penalties that operate on the latent space to ensure that the space contains the information we wish to encode.”
BackgroundDoudkin, A. A., Ganchenko, V. V., Inyutin, A., & Marushko, Y. (2023) · «System analysis and applied information science» · doi:10.21122/2309-4923-2022-4-30-37 · Cited by 2 · see citing works
Boettcher, W., Hoyer, L., Unal, O., Li, K., & Dai, D. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341349 · Cited by 2 · see citing works
“treat cross-modality information as some of the early works [17] did not manage to notably outperform depth prediction models when compared against each other.”
BackgroundContextual Embeddings and Graph Convolutional Networks for Concept Prerequisite Learning
Layoun, J.-C., Zouaq, A., & Desmarais, M. C. (2024) · ACM Symposium on Applied Computing · doi:10.1145/3605098.3636062
“The strategy of effectively learning multiple tasks with a single network, along with the selection of appropriate loss hyper-parameters, draws inspiration from existing work on Convolutional Neural Networks (CNNs) [10] and Cycle-GAN [32].”
BackgroundDB-SNet: A dual branch network for aortic component segmentation and lesion localization
Yang, M., Lyu, J., Hu, J., Bian, X., Zhang, Y., Su, S., & Lou, X. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102592
- Authors
- Kuga, R., Kanezaki, A., Samejima, M., Sugano, Y., & Matsushita, Y.
- Affiliations
- The University of Osaka (JP)
- National Institute of Advanced Industrial Science and Technology (JP)
- Venue
- 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 403-411
- ISSN
- 2473-9936 (ISSN-L)
- OpenAlex
- W2772409766
- Cited by
- 36
- References
- 33
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 6 · 2023: 4 · 2022: 6 · 2021: 3 · 2020: 6 · 2019: 5 · 2018: 3
- FWCI
- 1.12
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Computer Vision Workshops (publishedVersion)
- Tokyo Tech Research Repository (Tokyo Institute of Technology) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- multi-task learning, shared latent representation, cross-modal learning, semantic segmentation, depth estimation, scene understanding
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
