The DOI matches its Crossref record; 55 of the 64 references it cites were found in a registry or an index.
SceneGen: Learning to Generate Realistic Traffic Scenes
Open accessAbstract
We consider the problem of generating realistic traffic scenes automatically. Existing methods typically insert actors into the scene according to a set of hand-crafted heuristics and are limited in their ability to model the true complexity and diversity of real traffic scenes, thus inducing a content gap between synthesized traffic scenes versus real ones. As a result, existing simulators lack the fidelity necessary to train and test self-driving vehicles. To address this limitation, we present SceneGen—a neural autoregressive model of traffic scenes that eschews the need for rules and heuristics. In particular, given the ego-vehicle state and a high definition map of surrounding area, SceneGen inserts actors of various classes into the scene and synthesizes their sizes, orientations, and velocities. We demonstrate on two large-scale datasets SceneGen’s ability to faithfully model distributions of real traffic scenes. Moreover, we show that SceneGen coupled with sensor simulation can be used to train perception models that generalize to the real world.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Generating large synthetic datasets has been a problem of great interest in other domains as well [71-77], and has also been used as a tool for benchmarking motion planning [78].”
From MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations (2023) · cites this paper as [77]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“The basis of our model is the ConvLSTM architecture [42]—an extension of the classic LSTM architecture [22] to spatial data—and the input to our model at the i-th generation step is a bird’s eye view multi-channel image encoding the SDV a0, the HD map m, and the actors generated so far {a1, .”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 1×
“Each actor’s bounding box is sampled from a Gaussian KDE fitted to the training dataset [5] and velocities are set to satisfy speed limits and a time gap between successive actors on the lane graph.”
MethodGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W.-C. (2015) · arXiv · doi:10.48550/arxiv.1506.04214 · Cited by 7,709
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · cited 1×
“This is akin to the popular IS [41], FID [21], and KID [4] metrics for evaluating generative models, except we use a feature extractor trained on traffic scenes.”
MethodWaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 1×
“Recently, neural autoregressive models have found tremendous success in modeling a variety of data, including handwriting [18], images [49], audio [48], text [39], sketches [20], graphs [29], 3D meshes [33], indoor scenes [50] and image scene layouts [25].”
BackgroundCongested traffic states in empirical observations and microscopic simulations
Treiber, M., Hennecke, A., & Helbing, D. (2000) · Physical Review E · doi:10.1103/physreve.62.1805 · Cited by 4,762 · cited 1×
“In contrast, microscopic models simulate the behavior of each individual vehicle over time by assuming a car-following model [36, 6, 34, 13, 17, 1, 44].”
BackgroundOn kinematic waves II. A theory of traffic flow on long crowded roads
Lighthill, S. J., & Whitham, G. B. (1955) · Proceedings of the Royal Society of London A Mathematical and Physical Sciences · doi:10.1098/rspa.1955.0089 · Cited by 4,606
Microscopic Traffic Simulation using SUMO
López, P. Á., Wießner, E., Behrisch, M., Bieker-Walz, L., Erdmann, J., Flötteröd, Y.-P., Hilbrich, R., Lücken, L., Rummel, J., & Wagner, P. (2018) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569938 · Cited by 3,898 · cited 7×
“Microscopic traffic models have been included in popular software packages such as SUMO [31], CORSIM [35], VISSIM [11], and MITSIM [55].”
BackgroundMethodInfluentialCARLA: An open urban driving simulator
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V. (2017) · arXiv · doi:10.48550/arxiv.1711.03938 · Cited by 3,718 · cited 5×
“For example, the CARLA simulator [9] spawns actors at pre-determined locations and uses a lane-following controller to simulate the vehicle behaviors over time.”
BackgroundMethodInfluentialRichards, P. I. (1956) · Operations Research · doi:10.1287/opre.4.1.42 · Cited by 3,682 · cited 1×
“Macroscopic models simulate entire populations of vehicles in the aggregate [30, 40] to study “macroscopic” properties of traffic flow, such as traffic density and average velocity.”
Background(2012) · MPG.PuRe (Max Planck Society) · doi:10.5555/2188385.2188410 · Cited by 3,603
Dynamical model of traffic congestion and numerical simulation
Bando, M., Hasebe, K., Nakayama, A., Shibata, A., & Sugiyama, Y. (1995) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.51.1035 · Cited by 3,027 · cited 1×
“In contrast, microscopic models simulate the behavior of each individual vehicle over time by assuming a car-following model [36, 6, 34, 13, 17, 1, 44].”
BackgroundGenerating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894
Pattern recognition and machine learning
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5091 · Cited by 2,783
Pixel Recurrent Neural NetworksPreprint
van den Oord, A., Kalchbrenner, N., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.06759 · Cited by 1,793 · cited 4×
“This approach allows the model to express highly multimodal distributions without making assumptions about the distribution’s shape [49].”
BackgroundMethodInfluentialNonlinear Follow-the-Leader Models of Traffic Flow
Gazis, D. C., Herman, R., & Rothery, R. W. (1961) · Operations Research · doi:10.1287/opre.9.4.545 · Cited by 1,521 · cited 1×
“In contrast, microscopic models simulate the behavior of each individual vehicle over time by assuming a car-following model [36, 6, 34, 13, 17, 1, 44].”
BackgroundArgoverse: 3D Tracking and Forecasting With Rich Maps
Chang, M.-F., Lambert, J., Sangkloy, P., Singh, J., Bak, S., Hartnett, A., Wang, D., Carr, P., Lucey, S., Ramanan, D., et al. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00895 · Cited by 1,474 · cited 2×
“Argoverse: Argoverse [7] consists of two datasets collected by a fleet of SDVs in Pittsburgh and Miami.”
BackgroundMethodTraffic Dynamics: Studies in Car Following
Chandler, R. E., Herman, R., & Montroll, E. W. (1958) · Operations Research · doi:10.1287/opre.6.2.165 · Cited by 1,460 · cited 1×
“In contrast, microscopic models simulate the behavior of each individual vehicle over time by assuming a car-following model [36, 6, 34, 13, 17, 1, 44].”
BackgroundAn Operational Analysis of Traffic Dynamics
Pipes, L. A. (1953) · Journal of Applied Physics · doi:10.1063/1.1721265 · Cited by 1,314
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304 · cited 2×
“Therefore, we adopt a sampling strategy inspired by nucleus sampling [23].”
BackgroundMethodNonlinear Effects in the Dynamics of Car Following
Newell, G. F. (1961) · Operations Research · doi:10.1287/opre.9.2.209 · Cited by 1,111 · cited 1×
“In contrast, microscopic models simulate the behavior of each individual vehicle over time by assuming a car-following model [36, 6, 34, 13, 17, 1, 44].”
BackgroundDemystifying MMD GANsPreprint
Bińkowski, M., Sutherland, D. J., Arbel, M., & Gretton, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.01401 · Cited by 1,083 · cited 3×
“This is akin to the popular IS [41], FID [21], and KID [4] metrics for evaluating generative models, except we use a feature extractor trained on traffic scenes.”
MethodLearning Lane Graph Representations for Motion Forecasting
Liang, M., Yang, B., Hu, R., Chen, Y., Liao, R., Feng, S., & Urtasun, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_32 · Cited by 781 · cited 1×
“Similar to MetaSim, we also consider a learning-based version of Procedural that uses a lane graph neural network [28] to transform each actor’s position, bounding box, and velocity (Lane Graph).”
MethodSelf-citationA Microscopic Traffic Simulator for evaluation of dynamic traffic management systems
Yang, Q., & Koutsopoulos, H. N. (1996) · Transportation Research Part C Emerging Technologies · doi:10.1016/s0968-090x(96)00006-x · Cited by 746 · cited 4×
“Microscopic traffic models have been included in popular software packages such as SUMO [31], CORSIM [35], VISSIM [11], and MITSIM [55].”
BackgroundMethodInfluentialGraphRNN: Generating Realistic Graphs with Deep Auto-regressive ModelsPreprint
You, J., Ying, R., Ren, X., Hamilton, W. L., & Leskovec, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08773 · Cited by 612 · cited 1×
“Following [56, 29], we compute MMD using Gaussian kernels with the total variation distance to compare distributions of scene statistics between generated and real traffic scenes.”
MethodA Neural Representation of Sketch DrawingsPreprint
Ha, D., & Eck, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03477 · Cited by 538 · cited 1×
“Recently, neural autoregressive models have found tremendous success in modeling a variety of data, including handwriting [18], images [49], audio [48], text [39], sketches [20], graphs [29], 3D meshes [33], indoor scenes [50] and image scene layouts [25].”
Background(2020) · arXiv (Cornell University) · Cited by 461
Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
Prakash, A., Boochoon, S., Brophy, M., Acuna, D., Cameracci, E., State, G., Shapira, O., & Birchfield, S. T. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794443 · Cited by 304
LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
Manivasagam, S., Wang, S., Wong, K., Zeng, W., Sazanovich, M., Tan, S., Yang, B., Ma, W.-C., & Urtasun, R. (2020) · 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/cvpr42600.2020.01118 · Cited by 257 · cited 4×
“It enables us to build rich virtual environments in which we can improve our self-driving vehicles (SDVs) and verify their safety and performance [9, 31, 32, 53].”
BackgroundMethodInfluentialSelf-citationMeta-Sim: Learning to Generate Synthetic DatasetsPreprint
(2020) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 235
Deep convolutional priors for indoor scene synthesis
Wang, K., Savva, M., Chang, A. X., & Ritchie, D. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201362 · Cited by 220
HDNET: Exploiting HD Maps for 3D Object DetectionPreprint
Yang, B., Liang, M., & Urtasun, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.11704 · Cited by 220 · cited 3×
“ATG4D: ATG4D [54] is a large-scale dataset collected by a fleet of SDVs in cities across North America.”
BackgroundMethodSelf-citationEfficient Graph Generation with Graph Recurrent Attention NetworksPreprint
Liao, R., Li, Y., Song, Y., Wang, S., Nash, C., Hamilton, W. L., Duvenaud, D., Urtasun, R., & Zemel, R. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00760 · Cited by 210
Self-citationEfficient Simulation of the von Mises Distribution
Best, D. J., & Fisher, N. I. (1979) · Journal of the Royal Statistical Society Series C (Applied Statistics) · doi:10.2307/2346732 · Cited by 203 · cited 1×
“To sample from a mixture of Von-Mises distributions, we sample a component k from a categorical distribution and then sample θ from the Von-Mises distribution of the k-th component [3].”
MethodAugmented LiDAR Simulator for Autonomous Driving
Fang, J., Zhou, D., Yan, F., Zhao, T., Zhang, F., Ma, Y., Wang, L., & Yang, R. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2969927 · Cited by 163 · cited 2×
“An alternative approach is to learn a probabilistic distribution over traffic scenes from which we can sample new scenes [52, 51, 24, 10, 14, 15, 57].”
BackgroundMethodLayoutVAE: Stochastic Scene Layout Generation From a Label Set
Jyothi, A. A., Durand, T., He, J., Sigal, L., & Mori, G. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00999 · Cited by 153 · cited 11×
“LayoutVAE: Our implementation of LayoutVAE largely follows that of Jyothi et al .”
BackgroundMethodInfluentialRNADE: The real-valued neural autoregressive density-estimatorPreprint
Uría, B., Murray, I., & Larochelle, H. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.0186 · Cited by 140 · cited 1×
“Each conditional distribution is then approximated with a parameterized function [12, 2, 45, 46, 47].”
BackgroundModeling High-Dimensional Discrete Data with Multi-Layer Neural Networks
Bengio, Y., & Bengio, S. (1999) · Cited by 107
PolyGen: An Autoregressive Generative Model of 3D MeshesPreprint
Nash, C., Ganin, Y., Eslami, S. M. A., & Battaglia, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10880 · Cited by 101 · cited 1×
“Recently, neural autoregressive models have found tremendous success in modeling a variety of data, including handwriting [18], images [49], audio [48], text [39], sketches [20], graphs [29], 3D meshes [33], indoor scenes [50] and image scene layouts [25].”
BackgroundA Deep and Tractable Density Estimator
Uria, B., Murray, I., & Larochelle, H. (2013) · arXiv · doi:10.48550/arxiv.1310.1757 · Cited by 100 · cited 1×
“Each conditional distribution is then approximated with a parameterized function [12, 2, 45, 46, 47].”
Joint 3D Estimation of Objects and Scene Layout
Geiger, A., Wojek, C., & Urtasun, R. (2011) · Cited by 97
Self-citationDeep Directional Statistics: Pose Estimation with Uncertainty Quantification
Prokudin, S., Gehler, P., & Nowozin, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_33 · Cited by 89
Understanding High-Level Semantics by Modeling Traffic Patterns
Zhang, H., Geiger, A., & Urtasun, R. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.379 · Cited by 87 · cited 1×
“An alternative approach is to learn a probabilistic distribution over traffic scenes from which we can sample new scenes [52, 51, 24, 10, 14, 15, 57].”
Self-citationTraffic flow simulation using CORSIM
Owen, L. E., Zhang, Y., Rao, L., et al. (2002) · Winter Simulation Conference · doi:10.1109/wsc.2000.899077 · Cited by 84 · cited 2×
“Microscopic traffic models have been included in popular software packages such as SUMO [31], CORSIM [35], VISSIM [11], and MITSIM [55].”
MethodMeta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Devaranjan, J., Kar, A., & Fidler, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58520-4_42 · Cited by 73 · cited 2×
“MetaSim2 [8] extends this idea by learning to sample the scene graph as well.”
BackgroundMethodA generative model for 3D urban scene understanding from movable platforms
Geiger, A., Lauer, M., & Urtasun, R. (2011) · doi:10.1109/cvpr.2011.5995641 · Cited by 58 · cited 1×
“An alternative approach is to learn a probabilistic distribution over traffic scenes from which we can sample new scenes [52, 51, 24, 10, 14, 15, 57].”
BackgroundSelf-citationDoes the Wake-sleep Algorithm Produce Good Density Estimators?
Frey, B. J., Hinton, G. E., & Dayan, P. (1995) · MPG.PuRe (Max Planck Society) · Cited by 50
Generation of Scenes in Intersections for the Validation of Highly Automated Driving Functions
Jesenski, S., Stellet, J. E., Schiegg, F. A., et al. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8813776 · Cited by 35
Factor graph scene distributions for automotive safety analysis
Wheeler, T. A., & Kochenderfer, M. J. (2016) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2016.7795683 · Cited by 26
Initial Scene Configurations for Highway Traffic Propagation
Wheeler, T. A., Kochenderfer, M. J., & Robbel, P. (2015) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2015.55 · Cited by 22
Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
Wong, K., Zhang, Q., Liang, M., Yang, B., Liao, R., Sadat, A., & Urtasun, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58574-7_19 · Cited by 22
Self-citationMeta-Sim: Learning to Generate Synthetic Datasets
Kar, A., Prakash, A., Liu, M.-Y., Cameracci, E., Yuan, J., Rusiniak, M., Acuna, D., Torralba, A., & Fidler, S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00465 · Cited by 21 · cited 22×
“Finally, this modified scene graph is given as input to MetaSim, and we train MetaSim to transform the modified attributes back to their original ones.”
BackgroundMethodInfluentialGipps, P. G. (1976) · Cited by 10
Research works printed but not linked: 3
- gerlough, 1955, Simulation of Freeway Traffic on a General-Purpose Discrete Variable Computer
- uria, 2013, NADE: the real-valued neural autoregressive density-estimator, CoRR
- taheri, 1990, An investigation and design of slip control braking systems integrated with four wheel steering
Cited by
Sorted by citations
End-to-End Autonomous Driving: Challenges and Frontiers
Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., & Li, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3435937 · Cited by 843
“They can then generate novel scenarios that resemble the real world but were not included in the original data [96], [97], [98], [99].”
BackgroundGenerative artificial intelligence: a systematic review and applications
Sengar, S. S., Hasan, A. B., Kumar, S., & Carroll, F. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20016-1 · Cited by 763
“The model outperforms the previous state-of-art techniques such as SeneGen [127] in generating the synthetic traffic scenarios.”
3D Object Detection for Autonomous Driving: A Comprehensive Survey
Mao, J., Shi, S., Wang, X., & Li, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01790-1 · Cited by 529
“There are also some works simulating the traffic flows (Tan et al., 2021; Suo et al., 2021) or testing the safety of vehicles by simulation (Wong et al.”
BackgroundV2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving
Li, Y., Ma, D., An, Z., Wang, Z., Zhong, Y., Chen, S., & Feng, C. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3192802 · Cited by 381
A Survey on Safety-Critical Driving Scenario Generation—A Methodological Perspective
Ding, W., Xu, C., Arief, M., Lin, H., Li, B., & Zhao, D. X. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3259322 · Cited by 320
“introduced into the generation in [36] and [37].”
Background
Metadata
- Authors
- Tan, S., Wong, K., Wang, S., Manivasagam, S., Ren, M., & Urtasun, R.
- Affiliations
- Sun Yat-sen University (CN)
- University of Toronto (CA)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 892-901
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3173280621
- Semantic Scholar
- 8b817a28d880e4688956d6e1769475a9f22c7411
- Cited by
- 104
- References
- 64
- Citations by year
- 2026: 10 · 2025: 36 · 2024: 29 · 2023: 17 · 2022: 8 · 2021: 4
- FWCI
- 14.34
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Engineering › Control and Systems Engineering › Simulation and Modeling Applications
- Keywords
- autonomous driving simulation, high-definition maps, sensor simulation
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
