The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index; 1 of the 7 sources its claims cite were checked for support.
Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack
Open accessAbstract
Vehicle detection and tracking technology plays a crucial role in Intelligent Transportation Systems. However, due to factors such as complex scenarios, diverse scales, and occlusions, issues like false detections, missed detections, and identity switches frequently occur. To address these problems, this paper proposes a multi-object vehicle detection and tracking algorithm based on CDS-YOLOv8 and improved ByteTrack. For vehicle detection, the Context-Guided (CG) module is introduced during the downsampling process to enhance feature extraction capabilities in complex scenarios. The Dilated Reparam Block (DRB) is reconstructed to tackle multi-scale issues, and Soft-NMS replaces the traditional NMS to improve performance in densely populated vehicle scenarios. For vehicle tracking, the state vector and covariance matrix of the Kalman filter are improved to better handle the nonlinear movement of vehicles, and Gaussian Smoothed Interpolation (GSI) is introduced to fill in trajectory gaps caused by detection misses. Experiments conducted on the UA-DETRAC dataset show that the improved algorithm increases detection performance, with mAP@0.5 and mAP@0.5:0.95 improving by 9% and 8.8%, respectively. In terms of tracking performance, mMOTA improves by 6.7%. Additionally, comparative experiments with mainstream detection and two-stage tracking algorithms demonstrate the superior performance of the proposed algorithm.
Overview
CoChat Summary
TL;DR
The paper proposes CDS-YOLOv8, which adds Context-Guided downsampling, a reconstructed Dilated Reparam Block in C2f, and Soft-NMS, plus an improved ByteTrack with a modified Kalman filter and Gaussian Smoothed Interpolation. On UA-DETRAC, it reports detection mAP@0.5 and mAP@0.5:0.95 improvements of 9% and 8.8%, and tracking mMOTA improvement of 6.7%.
Key findings
- Detector ablation: baseline YOLOv8-S reached 64.2% mAP@0.5, 46.6% mAP@0.5:0.95, and 28.8 G Flops; final CDS-YOLOv8 reached 73.2% mAP@0.5, 55.4% mAP@0.5:0.95, and 26.6 G Flops, with P +10.6%, R +3.7%, mAP@0.5 +9%, mAP@0.5:0.95 +8.8%, and Flops reduced by 2.2 G.
- Detector comparison: CDS-YOLOv8 reported 73.2% mAP@0.5 and 55.4% mAP@0.5:0.95 at 26.6 G Flops, surpassing YOLOv9-S (65.1%, 48.0%, 39.6 G) and YOLOv8-L (71.6%, 51.4%, 165.7 G), with improvements of 1.6% and 4% over YOLOv8-L in mAP@0.5 and mAP@0.5:0.95.
- Tracker ablation: final CDS-YOLOv8 + ByteTrack + improved KF + GSI achieved 80.3% mIDF1, 530 IDS, and 73.9% mMOTA, versus YOLOv8s + ByteTrack at 76.9% mIDF1, 855 IDS, and 67.2% mMOTA; overall mIDF1 +3.4%, IDS −325, mMOTA +6.7%.
- Tracker comparison: improved ByteTrack reported 80.3% mIDF1, 530 IDS, and 73.9% mMOTA, compared with BoT-SORT at 78.6%, 727, and 72.9%; the paper notes its method does not use ReID.
Methods
- Dataset: UA-DETRAC, with 10 h of video at 25 fps, over 140,000 frames and 1.21 million annotated boxes; training set 60 sequences/83,791 images and test set 40 sequences/56,340 images. After excluding unlabeled images and sampling every 10th frame, 8209 images were used for training and 5617 for evaluation; tracking used 40 test video sequences.
- Model: YOLOv8-S baseline; CG module introduced during downsampling; reconstructed DRB integrated with C2f; Soft-NMS replaces traditional NMS. Tracking uses ByteTrack as base, with improved Kalman filter state vector using center coordinates, width, and height plus time-varying Q and R, and GSI using Gaussian Process Regression/RBF to fill trajectory gaps; unmatched tracklets are deleted after more than 30 frames.
- Training/evaluation: RTX 4090, Core i9-9900K @ 3.60 GHz, Windows 10, PyTorch 1.31.1, CUDA 11.6, Python 3.8; 200 epochs, batch size 32, no pre-trained weights. Detection metrics: P, R, mAP@0.5, mAP@0.5:0.95; tracking metrics: MOTA, IDF1, IDS.
Limitations
- The paper does not explicitly state limitations; it only states future work will explore infrared images, radar, and other modalities.
- Evident from the text: all reported experiments use only the UA-DETRAC dataset, with no cross-dataset or real-world deployment validation reported.
- Evident from the text: no runtime, FPS, or speed measurements are reported, despite claims about balancing tracking speed and accuracy and about ReID reducing operating speed.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 1 Not valid · 6 Not checked · 47 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For vehicle detection, the Context-Guided (CG) module is introduced during the downsampling process to enhance feature extraction capabilities in complex scenarios.”
- Also stated in: § 1. Introduction · plain
“This algorithm introduces the Context-Guided module [14] during the downsampling process to enhance feature extraction capabilities, thereby adapting to complex scene variations.”
- Also stated in: § 3. Methods · plain
“The CG module is introduced during downsampling, which enhances feature extraction in complex environments by combining local and surrounding contextual information and utilizing global information for weighting.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > Abstract
What the sources say
- Partly supportedcites [14] Wu, 2021, CGNet: A Light-Weight Context Guided Network for Semantic Segmentation, IEEE Trans. Image Process. sourceExperimental — accuracy not yet measured
Section 3.2 (p. 5) says CG blocks are used in stages 2 and 3 to downsample feature maps, and Section 3.1 (p. 4) describes how they combine local features with surrounding and global context. The paper develops and evaluates the blocks for semantic segmentation, not vehicle detection; it does not establish the claimed enhancement for vehicle detection in complex scenarios. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Also stated in: § 1. Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experiments conducted on the UA-DETRAC dataset show that the improved algorithm increases detection performance, with mAP@0.5 and mAP@0.5:0.95improving by 9% and 8.8%, respectively.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experiments conducted on the UA-DETRAC dataset show that the improved algorithm increases detection performance, with mAP@0.5 and mAP@0.5:0.95improving by 9% and 8.8%, respectively.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Additionally, comparative experiments with mainstream detection and two-stage tracking algorithms demonstrate the superior performance of the proposed algorithm.”
- Also stated in: § 3. · boosted
“Experimental results indicate that this method demonstrates advanced performance and superiority across multiple metrics.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > Abstract
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3. · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In terms of tracking performance, mMOTA improves by 6.7%.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
19 more claims
Create a free account to see all 55 claims and every source verdict.
- It may state two separate claims as one. 29
- Probably not a substantial claim. 7
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > 3.4. Improved Kalman Filter
“where σ p is the standard deviation of position noise and σ p is the standard deviation of velocity noise.”
§ Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack > 3.4. Improved Kalman Filter
“σ v ŵk-1|k-1 2 , σ v ĥk-1|k-1 2 , σ v ŵk-1|k-1 2 , σ v ĥk-1|k-1 2”
Citations
Cites
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370
Simple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Wang, C.-Y., Yeh, I.-H., & Mark Liao, H.-Y. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72751-1_1 · Cited by 4,823
YOLOv9: Learning What You Want to Learn Using Programmable Gradient InformationPreprint
Wang, C.-Y., Yeh, I.-H., & Liao, H. (2024) · European Conference on Computer Vision · doi:10.48550/arxiv.2402.13616 · Cited by 4,701
Cited by
Kamil, D. A., Wahyono, W., Harjoko, A., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3508135 · Cited by 15
Autonomous Agricultural Robot Using YOLOv8 and ByteTrack for Weed Detection and Destruction
Bajraktari, A., & Toylan, H. (2025) · Machines · doi:10.3390/machines13030219 · Cited by 18
RE-YOLO: Vehicle Detector Based on Knowledge Distillation YOLOv8 for Autonomous Driving Scenarios
Xie, Y., Du, D., & Yang, L. Z. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6164 · Cited by 13
Wei, X., Zhao, C., Liu, X., et al. (2025) · Journal of Control and Decision · doi:10.1080/23307706.2025.2569552 · Cited by 6
Study on Nighttime Pedestrian Trajectory-Tracking from the Perspective of Driving Blind Spots
Zhao, W., Ren, C., & Tan, A. (2024) · Electronics · doi:10.3390/electronics13173460 · Cited by 5
SPT: Obtaining long trajectory data of disordered traffic using a swarm of unmanned aerial vehicles
Rajput, S., Venkateshappa, S., Kanagaraj, V., Asaithambi, G., & Treiber, M. (2025) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2025.105431 · Cited by 9
Khan, M. R. K., & Rishe, N. D. (2026) · Remote Sensing · doi:10.3390/rs18050842 · Cited by 6
Wang, B., Zhou, Y., Sui, H., Ma, G., Cheng, P., & Wang, D. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.01.038 · Cited by 4
Porto, J. V. D. A., Szemes, P. T., Pistori, H., & Menyhárt, J. (2025) · IEEE Access · doi:10.1109/access.2025.3565901 · Cited by 4
“While studies such as those by [14] and [15] adopted standard classification and detection metrics, others opted for alternative metrics, such as the ‘‘S4’’ proposed by [16] and the ‘‘MR’’ used by [27] and [29].”
Mitra, R., Sourav, M. A. A., Kim, S., Gülmezoğlu, B., & Ceylan, H. (2025) · ASCE International Conference on Transportation and Development (ICTD) · doi:10.1061/9780784486191.027 · Cited by 5
Vehicle Classification Using YOLOv8: A Deep Learning Framework for Real-Time Traffic Monitoring
Raj, R. A. P., Swapna, R., Rakheeb, M. F., et al. (2025) · International Conference on Data Science and Network Security (ICDSNS) · doi:10.1109/icdsns65743.2025.11168795 · Cited by 1
Sustainable Real-Time Urban Mobility with Attention-Based YOLOv5s and Refined Deep SORT Algorithm
Sherin, B. C., & Poovammal, E. (2025) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-025-02477-y · Cited by 1
Hao, T., Xu, L., Feng, H., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.119977 · Cited by 1
Sun, N., Yang, X., Xie, M., et al. (2026) · Animals · doi:10.3390/ani16101479 · Cited by 1
Laryushin, T. V., Galkin, V. A., & Zhabinskaya, V. P. (2025) · Achievements of Science and Technology in Agro-Industrial Complex · doi:10.53859/02352451_2025_39_10_69 · Cited by 1
Counting vehicles types using deep learning algorithm in video surveillance systems
Akoushideh, A., Sadat, S. S., & Shahbahrami, A. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20530-2 · Cited by 2
Enhanced Real-Time Object Detection on Customized Dataset with YOLOv9 Architecture
Adithiyan, P. V., Manoharan, R. K., Rahul, K., et al. (2024) · doi:10.1109/inspect63485.2024.10896201 · Cited by 1
“[19].”
Li, X., Jia, Y., Li, Y., et al. (2025) · Materials Reports Solidwaste and Ecomaterials · doi:10.26599/mrse.2025.9520017
DCGF-YOLOv8: a lightweight and multi-scale model for wind turbine blade surface defect detection
Wang, Y., Zheng, Y., Cao, Y., Liu, Y., & Cui, T. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2ce5
Real-Time Aircraft Detection and Tracking Using YOLOv11+BoT-SORT for National Defense
Dinisfusya’Ban, Suharjo, B., Indrajit, R. E., & Rimbawa, H. A. D. (2025) · IEEE International Conference on Computing, Engineering and Design (ICCED) · doi:10.1109/icced68324.2025.11324556
“This metric evaluates detection and tracking accuracy by combining false positives, false negatives, and ID switches; higher scores reflect stable performance [32]. d) Mean IoU quantifies the average overlap between predicted and ground-truth boxes.”
Predictive Modeling of Vehicle Emissions Using Deep Learning Techniques and AERMOD
Yavuz, E., Öztürk, A., Balkanlı, N. G. N., et al. (2026) · Springer proceedings in complexity · doi:10.1007/978-3-032-02971-3_50
Vision-based Multi-Object Tracking for Unstructured and Congested Indian Roads
Lekshmi, V., & Naveen Prasad, S. (2025) · doi:10.1109/icrm66809.2025.11349048
“Methods such as Gaussian Smoothed Interpolation (GSI) are also proposed to compensate for trajectory gaps due to lost detections to maximize continuity [14].”
YOLC with dynamic sparse attention for high-speed small target detection in wearable sports images
Hui Cheng, C. H. E. N., Song, Y., Liu, W., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-38079-5
Obstacle Detection and Tracking Framework for Autonomous Mobile Robots
Van, N. C., Huy, N. D. Q., Binh, N. D., et al. (2026) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3180/1/012069
“Recent work by You et al. [11] demonstrated signi0icant improvements in traf0ic scenarios through co-designed detection and tracking, achieving mMOTA of 73.9% and mIDF1 of 80.3%.”
InfluentialFishTally: Automated fish detection and counting tool
Maniyambath, A., & Krishnan, R. (2026) · SoftwareX · doi:10.1016/j.softx.2026.102643
A Multi-Object Tracking Algorithm Based on an Improved YOLOv8 and ByteTrack
Huang, M., & Wei, C. (2026) · doi:10.1109/iscait69154.2026.11477334
Gu, H., Yu, L., Li, H., & Chen, M. (2026) · Marine Biotechnology · doi:10.1007/s10126-026-10620-7
“This environmental noise explains why the baseline ByteTrack algorithm exhibited a relatively low MOTA of 65.495% and high ID switches in our trials.”
InfluentialJumah, Z. H., & Chyaid, A. M. (2026) · African Journal Of Applied Research · doi:10.26437/mqagpa72
“The architecture of YOLOv8 is based on single-stage object detectors that directly predict the bounding boxes and class probabilities in one pass without relying upon region proposal networks, and as a result, it produces more efficient inference (You et al., 2024).”
A Comparative Study of Hardware Accelerators for Autonomous Vehicles in Recent ADAS Practices
Chaman, M., Yanboiy, H. E., Dahou, H., Gouri, R. E., Hlou, L., & Hadjoudja, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-0888-1.ch004
Kutyrev, A. I., & Potapenkov, N. A. (2026) · Horticulture and viticulture · doi:10.31676/0235-2591-2026-2-48-59
Vehicle Color-Type Detection Based on YOLOv8 and K-Means
Çiçek, İ., Apaydın, N. N., Kılıç, İ., et al. (2026) · Journal of Physical Chemistry and Functional Materials · doi:10.54565/jphcfum.1951468
Vehicle Detection: A Comparative Study of YOLO Models in Vehicle Detection
Lokaraj, R., Adhithiyan, B., Guruprasanna, S., & Selvam, P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-25952-3_38
Modeling and benchmarking two-wheeler seepage behavior in dense mixed traffic simulations
Guin, A., Bazán-Guillén, A., Kannan, P., et al. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112510
Lightweight Deep Learning Framework for Traffic Accidents Detection: A Review
Abbas, Y. J., Al-Khalidi, F. Q., & Shaker, S. H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23317-2_41
Wang, J., Liu, X., Deng, H., Yu, R., & Yang, W. (2026) · Vehicles · doi:10.3390/vehicles8080185
“…including YOLOv8l and BoT-SORT, can support trajectory extraction under the occlusion and density conditions observed on Hanoi arterials [19,20], building on a longer tradition of using fixed roadside cameras and homo-graphic ground-plane projection and trajectory reconstruction methods to…”
Drone-Based Vehicle Detection Using YOLOv11 for Urban Traffic Monitoring in Bandung, Indonesia
Naufan, M. R., & Bayuwindra, A. (2026) · doi:10.1109/icsmech69390.2026.11647140
“Various studies have explored different YOLO variants, such as YOLOv5 and YOLOv8, often combined with tracking algorithms to support advanced traffic analysis applications [3][4][5][6].”
Kenzari, Y., Fan, Y., & Ju, D. (2026) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr69988.2026.11642692
“The DRB has been restructured and combined with the C2f module [12], while the Select Kernel (SK) attention mechanism was used as a way of enhancing the emphasis and detection of important features [13].”
Streamlined Multi-Object Tracking With Fuzzy Kalman Filtering and Shape-Aware Association Strategies
Razzaq, S., Khan, M. I., Dar, A. R., & Razzaq, S. (2026) · IEEE Access · doi:10.1109/access.2026.3732189
“In the area of vehicle tracking, the authors in [40] combined an improved YOLOv8 model (CDS-YOLOv8) with ByteTrack.”
Prabhakar, E. A. A. D. B. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-38516
Metadata
- Authors
- You, L., Chen, Y., Xiao, C., Sun, C., & Li, R.
- Affiliations
- China West Normal University (CN)
- Corresponding author
- Chen, Yajun
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2024-08-01
- Volume
- 13
- Issue
- 15
- Pages
- 3033
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W4401211089
- Cited by
- 42
- References
- 37
- Citations by year
- 2026: 24 · 2025: 14 · 2024: 4
- FWCI
- 5.85
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- Funders
- China West Normal University (463177)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- vehicle detection, multi-target tracking, YOLOv8, ByteTrack, multi-scale feature extraction, Soft-NMS, Kalman filter, occlusion handling, identity switching, intelligent transportation systems, UA-DETRAC
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.