BRAND: a platform for closed-loop experiments with deep network models
Open accessPublished version of a preprint
The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Objective. Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g. Python and Julia) while maintaining support for languages that are critical for low-latency data acquisition and processing (e.g. C and C++). Approach. To address these needs, we introduce the Backend for Realtime Asynchronous Neural Decoding (BRAND). BRAND comprises Linux processes, termed nodes , which communicate with each other in a graph via streams of data. Its asynchronous design allows for acquisition, control, and analysis to be executed in parallel on streams of data that may operate at different timescales. BRAND uses Redis, an in-memory database, to send data between nodes, which enables fast inter-process communication and supports 54 different programming languages. Thus, developers can easily deploy existing ANN models in BRAND with minimal implementation changes. Main results. In our tests, BRAND achieved <600 microsecond latency between processes when sending large quantities of data (1024 channels of 30 kHz neural data in 1 ms chunks). BRAND runs a brain-computer interface with a recurrent neural network (RNN) decoder with less than 8 ms of latency from neural data input to decoder prediction. In a real-world demonstration of the system, participant T11 in the BrainGate2 clinical trial (ClinicalTrials.gov Identifier: NCT00912041) performed a standard cursor control task, in which 30 kHz signal processing, RNN decoding, task control, and graphics were all executed in BRAND. This system also supports real-time inference with complex latent variable models like Latent Factor Analysis via Dynamical Systems. Significance. By providing a framework that is fast, modular, and language-agnostic, BRAND lowers the barriers to integrating the latest tools in neuroscience and machine learning into closed-loop experiments.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures



![Figure 4. BRAND runs ANN latent variable models with low latency. (a) To test the inference latency of LFADS and NDT, we inserted them into an iBCI control graph that receives 256 channels of simulated threshold crossings at 1 kHz, bins them, runs inference with LFADS or NDT, runs decoding, and updates the task state. Both LFADS and NDT used a sequence length of 30 bins. (b) LFADS and NDT use different types of sequence models, an RNN and a Transformer, respectively. Reprinted from Ye and Pandarinath 2021 [19]. (c) NDT inference times were consistently below 2 ms, while LFADS inference times were consistently below 6 ms. Reproduced from [19]. CC BY 4.0.](https://figures.cochat.ai/paper-figures/ef420fe7fb0a4d1a9532e22239c2e96d/brand-a-platform-for-closed-loop-experiments-with-deep-network-models-figure-4.jpg)

Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Topological domains in mammalian genomes identified by analysis of chromatin interactions
Dixon, J. R., Selvaraj, S., Yue, F., Kim, A., Li, Y., Shen, Y., Hu, M., Liu, J. S., & Ren, B. (2012) · Nature · doi:10.1038/nature11082 · Cited by 6,829
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
BCI2000: A General-Purpose Brain-Computer Interface (BCI) System
Schalk, G., McFarland, D. J., Hinterberger, T., Birbaumer, N., & Wolpaw, J. R. (2004) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.827072 · Cited by 3,024
Reach and grasp by people with tetraplegia using a neurally controlled robotic arm
Hochberg, L. R., Bacher, D., Jarosiewicz, B., Masse, N. Y., Simeral, J. D., Vogel, J., Haddadin, S., Liu, J., Cash, S. S., van der Smagt, P., et al. (2012) · Nature · doi:10.1038/nature11076 · Cited by 2,719 · cited 1×
“In research with intracortical BCIs (iBCI), closed-loop systems have enabled people with paralysis to control a robotic arm, spell sentences, move limbs with functional electrical stimulation, and speak [1]–[6].”
BackgroundSelf-citationHigh-performance neuroprosthetic control by an individual with tetraplegia
Collinger, J. L., Wodlinger, B., Downey, J. E., Wang, W., Tyler-Kabara, E. C., Weber, D. J., McMorland, A. J., Velliste, M., Boninger, M. L., & Schwartz, A. B. (2013) · The Lancet · doi:10.1016/s0140-6736(12)61816-9 · Cited by 1,848
Direct Cortical Control of 3D Neuroprosthetic Devices
Taylor, D. M., Tillery, S. I. H., & Schwartz, A. B. (2002) · Science · doi:10.1126/science.1070291 · Cited by 1,540 · cited 1×
“The intended cursor velocity was approximated as the vector resulting from subtracting the cursor’s position from the target’s position scaled to the original OLE prediction’s magnitude or zeroed if the cursor reached the target [23].”
MethodHigh-performance brain-to-text communication via handwriting
Willett, F. R., Avansino, D. T., Hochberg, L. R., Henderson, J. M., & Shenoy, K. V. (2021) · Nature · doi:10.1038/s41586-021-03506-2 · Cited by 1,024
Self-citationAjiboye, A. B., Willett, F. R., Young, D. R., Memberg, W. D., Murphy, B. A., Miller, J. P., Walter, B. L., Sweet, J. A., Hoyen, H. A., Keith, M. W., et al. (2017) · The Lancet · doi:10.1016/s0140-6736(17)30601-3 · Cited by 862
Self-citationInferring single-trial neural population dynamics using sequential auto-encoders
Pandarinath, C., O’Shea, D. J., Collins, J., Jozefowicz, R., Stavisky, S. D., Kao, J. C., Trautmann, E. M., Kaufman, M. T., Ryu, S. I., Hochberg, L. R., et al. (2018) · Nature Methods · doi:10.1038/s41592-018-0109-9 · Cited by 686 · cited 2×
“To further evaluate the advanced ANN inference capabilities that BRAND provides, we sought to benchmark the latencies of two state-of-the-art latent variable models: LFADS and NDT [19, 20].”
MethodSelf-citationBonsai: an event-based framework for processing and controlling data streams
Lopes, G., Bonacchi, N., Frazão, J., Neto, J. P., Atallah, B. V., Soares, S., Moreira, L., Matias, S., Itskov, P. M., Correia, P. A., et al. (2015) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2015.00007 · Cited by 593 · cited 1×
“Previous real-time systems that lacked Python support would have required a full reimplementation of these models in another language like C or C ++ to run this test [11, 27].”
MethodNeuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria
Moses, D. A., Metzger, S. L., Liu, J. R., Anumanchipalli, G. K., Makin, J. G., Sun, P. F., Chartier, J., Dougherty, M. E., Liu, P. M., Abrams, G. M., et al. (2021) · New England Journal of Medicine · doi:10.1056/nejmoa2027540 · Cited by 582 · cited 1×
“BRAND also fills a critical need in speech iBCI research, where artificial neural networks have enabled several recent advances in brain-to-text decoding [6], [32] and are anticipated to play an important role in the development of real-time speech synthesis BCIs [33].”
BackgroundA high-performance speech neuroprosthesis
Willett, F. R., Kunz, E. M., Fan, C., Avansino, D. T., Wilson, G. H., Choi, E. Y., Kamdar, F., Glasser, M. F., Hochberg, L. R., Druckmann, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06377-x · Cited by 581
Self-citationPandarinath, C., Nuyujukian, P., Blabe, C. H., Sorice, B. L., Saab, J., Willett, F. R., Hochberg, L. R., Shenoy, K. V., & Henderson, J. M. (2017) · eLife · doi:10.7554/elife.18554 · Cited by 566 · cited 3×
“From a latency perspective, the Simulink real-time systems most commonly used for iBCI studies have been reported to have an end-to-end latency of 13–20 ms for cursor control [3, 7].”
BackgroundMethodSelf-citationA high-performance neural prosthesis enabled by control algorithm design
Gilja, V., Nuyujukian, P., Chestek, C. A., Cunningham, J. P., Yu, B. M., Fan, J. M., Churchland, M. M., Kaufman, M. T., Kao, J. C., Ryu, S. I., et al. (2012) · Nature Neuroscience · doi:10.1038/nn.3265 · Cited by 564 · cited 1×
“We then trained an OLE decoder to predict the cursor’s velocity from neural data [23].”
Simeral, J. D., Kim, S.-P., Black, M. J., Donoghue, J. P., & Hochberg, L. R. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/2/025027 · Cited by 496
Self-citationClinical translation of a high-performance neural prosthesis
Gilja, V., Pandarinath, C., Blabe, C. H., Nuyujukian, P., Simeral, J. D., Sarma, A. A., Sorice, B. L., Perge, J. A., Jarosiewicz, B., Hochberg, L. R., et al. (2015) · Nature Medicine · doi:10.1038/nm.3953 · Cited by 343 · cited 4×
“Systems like Simulink Real-Time [6], RTXI [10], and Falcon [11] provide tight timing guarantees but lack the Python support that is essential for machine learning research.”
BackgroundMethodResultInfluentialSelf-citationA high-performance speech neuroprosthesisPreprint
Willett, F. R., Kunz, E. M., Fan, C., et al. (2023) · bioRxiv · doi:10.1101/2023.01.21.524489 · Cited by 284 · cited 2×
“BRAND also fills a critical need in speech iBCI research, where artificial neural networks have enabled several recent advances in brain-to-text decoding [6], [32] and are anticipated to play an important role in the development of real-time speech synthesis BCIs [33].”
BackgroundModeling behaviorally relevant neural dynamics enabled by preferential subspace identification
Sani, O. G., Abbaspourazad, H., Wong, Y. T., Pesaran, B., & Shanechi, M. M. (2020) · Nature Neuroscience · doi:10.1038/s41593-020-00733-0 · Cited by 202 · cited 1×
“The development of new computational models is a critical avenue for studying neural activity across several brain functions, including movement, sensation, and cognition [34], [35].”
BackgroundCunningham, J. P., Nuyujukian, P., Gilja, V., Chestek, C. A., Ryu, S. I., & Shenoy, K. V. (2011) · Journal of Neurophysiology · doi:10.1152/jn.00503.2010 · Cited by 176 · cited 2×
“For applications such as using an iBCI to control a computer cursor, the latency from neural recording to behavioral prediction has typically been 15-20 ms [3], [7]; increasing latency is known to decrease control performance [8], [9].”
BackgroundMethodSimeral, J. D., Hosman, T., Saab, J., Flesher, S. N., Vilela, M., Franco, B., Kelemen, J. N., Brandman, D. M., Ciancibello, J. G., Rezaii, P. G., et al. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3069119 · Cited by 165 · cited 1×
“Future Directions While the experiments shown in this study were conducted on stereotyped block design-based tasks, BRAND could potentially be extended to personal use settings [31], where the participant would use an iBCI for their daily activities.”
Self-citationNeural Latents Benchmark '21: Evaluating latent variable models of neural population activityPreprint
Pei, F., Ye, J., Zoltowski, D. M., Wu, A., Chowdhury, R. H., Sohn, H., O’Doherty, J. E., Shenoy, K. V., Kaufman, M. T., Churchland, M. M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04463 · Cited by 158 · cited 1×
“…the extraction of neural features for use in decoding, and have previously achieved a velocity prediction R 2 of 0.9097 and 0.8862, respectively in the ‘MC_Maze 5 ms’ data-set in the Neural Latents Benchmark [26], which is a marked improvement over the 0.6238 achieved using smoothed binned spikes.”
MethodInfluentialSelf-citationRapid calibration of an intracortical brain–computer interface for people with tetraplegia
Brandman, D. M., Hosman, T., Saab, J., Burkhart, M. C., Shanahan, B. E., Ciancibello, J. G., Sarma, A. A., Milstein, D. J., Vargas-Irwin, C. E., Franco, B., et al. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aa9ee7 · Cited by 153
Self-citationStavisky, S. D., Kao, J. C., Nuyujukian, P., Ryu, S. I., & Shenoy, K. V. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/3/036009 · Cited by 137 · cited 1×
“For example, closed-loop feedback is known to be a critical component of iBCI control, so, in the iBCI context, offline analysis can provide only a partial validation of a decoding model [8], [12].”
BackgroundSelf-citationKeshtkaran, M. R., Sedler, A. R., Chowdhury, R. H., Tandon, R., Basrai, D., Nguyen, S. L., Sohn, H., Jazayeri, M., Miller, L. E., & Pandarinath, C. (2022) · Nature Methods · doi:10.1038/s41592-022-01675-0 · Cited by 127 · cited 1×
“The development of new computational models is a critical avenue for studying neural activity across several brain functions, including movement, sensation, and cognition [34], [35].”
BackgroundSelf-citationRapid control and feedback rates enhance neuroprosthetic control
Shanechi, M. M., Orsborn, A. L., Moorman, H. G., Gowda, S., Dangi, S., & Carmena, J. M. (2017) · Nature Communications · doi:10.1038/ncomms13825 · Cited by 120 · cited 1×
“For applications such as using an iBCI to control a computer cursor, the latency from neural recording to behavioral prediction has typically been 15-20 ms [3], [7]; increasing latency is known to decrease control performance [8], [9].”
MethodNason, S. R., Vaskov, A. K., Willsey, M. S., Welle, E. J., An, H., Vu, P. P., Bullard, A. J., Nu, C. S., Kao, J. C., Shenoy, K. V., et al. (2020) · Nature Biomedical Engineering · doi:10.1038/s41551-020-0591-0 · Cited by 113 · cited 1×
“The OLE decoder had a 384-dimensional input consisting of threshold crossings and spike-band power [17] from 192 channels of neural data.”
MethodReview: Human Intracortical Recording and Neural Decoding for Brain–Computer Interfaces
Brandman, D. M., Cash, S. S., & Hochberg, L. R. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2017.2677443 · Cited by 103 · cited 1×
“The decoder’s cursor velocity predictions were smoothed with an exponential moving average and scaled before the cursor position and task state were updated (Fig 3a, Fig S1a) [15], [16].”
MethodSelf-citationRepresentation learning for neural population activity with Neural Data Transformers
Ye, J., & Pandarinath, C. (2021) · Neurons Behavior Data analysis and Theory · doi:10.51628/001c.27358 · Cited by 98 · cited 7×
“To further evaluate the advanced ANN inference capabilities that BRAND provides, we sought to benchmark the latencies of two state-of-the-art latent variable models: LFADS and NDT [19, 20].”
BackgroundMethodInfluentialSelf-citationThe science and engineering behind sensitized brain-controlled bionic hands
Pandarinath, C., & Bensmaïa, S. J. (2021) · Physiological Reviews · doi:10.1152/physrev.00034.2020 · Cited by 90 · cited 1×
“The decoder’s cursor velocity predictions were smoothed with an exponential moving average and scaled before the cursor position and task state were updated (Fig 3a, Fig S1a) [15], [16].”
MethodSelf-citationHard real-time closed-loop electrophysiology with the Real-Time eXperiment Interface (RTXI)
Patel, Y. A., George, A., Dorval, A. D., White, J. A., Christini, D. J., & Butera, R. J. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005430 · Cited by 66 · cited 4×
“Systems like Simulink Real-Time [6], RTXI [10], and Falcon [11] provide tight timing guarantees but lack the Python support that is essential for machine learning research.”
BackgroundInfluentialQuickest detection of drug-resistant seizures: An optimal control approach
Santaniello, S., Burns, S. P., Golby, A. J., Singer, J. M., Anderson, W. S., & Sarma, S. V. (2011) · Epilepsy & Behavior · doi:10.1016/j.yebeh.2011.08.041 · Cited by 58 · cited 1×
“Advances in modeling and decoding neural activity could lead to therapeutic benefits if paired with devices that interface with the brain, like responsive neurostimulators for epilepsy [38].”
BackgroundFalcon: a highly flexible open-source software for closed-loop neuroscience
Ciliberti, D., & Kloosterman, F. (2017) · Journal of Neural Engineering · doi:10.1088/1741-2552/aa7526 · Cited by 44 · cited 3×
“Systems like Simulink Real-Time [6], RTXI [10], and Falcon [11] provide tight timing guarantees but lack the Python support that is essential for machine learning research.”
BackgroundMethodKeshtkaran, M. R., Sedler, A. R., Chowdhury, R. H., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.01.13.426570 · Cited by 33
Clisson, P., Bertrand-Lalo, R., Congedo, M., Victor-Thomas, G., & Chatel-Goldman, J. (2019) · HAL · doi:10.3217/978-3-85125-682-6-17 · Cited by 25 · cited 1×
“Timeflux [28] and LabGraph [29] solely support Python, and thus suffer from the lack of support for lower-level languages like C that are more suitable for latency-critical applications.”
BackgroundSynthesizing Speech by Decoding Intracortical Neural Activity from Dorsal Motor Cortex
Wairagkar, M., Hochberg, L. R., Brandman, D. M., & Stavisky, S. D. (2023) · 2023 11th International IEEE/EMBS Conference on Neural Engineering (NER) · doi:10.1109/ner52421.2023.10123880 · Cited by 22 · cited 4×
“BRAND also fills a critical need in speech iBCI research, where artificial neural networks have enabled several recent advances in brain-to-text decoding [6], [32] and are anticipated to play an important role in the development of real-time speech synthesis BCIs [33].”
BackgroundInfluentialSelf-citationAn open-source realtime computational platform (short WIP paper)
Mehrotra, P., Dasgupta, S., Robertson, S., & Nuyujukian, P. (2018) · ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) · doi:10.1145/3211332.3211344 · Cited by 4 · cited 2×
“LiCoRICE provides Python and C support, but does so via a custom shared memory interface instead of Redis [12].”
MethodProject dareplane for closed-loop deep brain stimulation
Dold, M., Pereira, J. B., Janssen, M., & Tangermann, M. (2023) · Brain stimulation · doi:10.1016/j.brs.2023.01.591 · Cited by 3 · cited 1×
“Dareplane, another recently-published real-time framework has been designed to provide broad language compatibility, but unlike BRAND, it has not been validated to support the high-bandwidth communication needed for iBCIs that contain hundreds of channels [30].”
Method(2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings
Cited by
An Accurate and Rapidly Calibrating Speech Neuroprosthesis
Card, N. S., Wairagkar, M., Iacobacci, C., Hou, X., Singer-Clark, T., Willett, F. R., Kunz, E. M., Fan, C., Vahdati Nia, M., Deo, D. R., et al. (2024) · New England Journal of Medicine · doi:10.1056/nejmoa2314132 · Cited by 268
Self-citationThe lab streaming layer for synchronized multimodal recording
Kothe, C., Shirazi, S. Y., Stenner, T., Medine, D., Boulay, C., Grivich, M. I., Artoni, F., Mullen, T., Delorme, A., & Makeig, S. (2025) · Imaging Neuroscience · doi:10.1162/imag.a.136 · Cited by 195
“For example, BRAND reported up to 0.5 ms in its “inter-node” communication, that is, prior to running additional processing or feature extraction pipelines ( Ali et al., 2023).”
InfluentialAn instantaneous voice-synthesis neuroprosthesis
Wairagkar, M., Card, N. S., Singer-Clark, T., Hou, X., Iacobacci, C., Miller, L. M., Hochberg, L. R., Brandman, D. M., & Stavisky, S. D. (2025) · Nature · doi:10.1038/s41586-025-09127-3 · Cited by 148
Self-citationStabilizing brain-computer interfaces through alignment of latent dynamics
Karpowicz, B. M., Ali, Y. H., Wimalasena, L. N., Sedler, A. R., Keshtkaran, M. R., Bodkin, K. L., Ma, X., Rubin, D. B., Williams, Z. M., Cash, S. S., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-59652-y · Cited by 114
Self-citationStabilizing brain-computer interfaces through alignment of latent dynamics
Karpowicz, B. M., Ali, Y. H., Wimalasena, L. N., Sedler, A. R., Keshtkaran, M. R., Bodkin, K., Ma, X., Miller, L. E., & Pandarinath, C. (2022) · doi:10.1101/2022.04.06.487388 · Cited by 71
Self-citation
Metadata
- Authors
- Ali, Y. H., Bodkin, K., Rigotti-Thompson, M., Patel, K., Card, N. S., Bhaduri, B., Nason-Tomaszewski, S. R., Mifsud, D. M., Hou, X., Nicolas, C., Allcroft, S., Hochberg, L. R., Au Yong, N., Stavisky, S. D., Miller, L. E., Brandman, D. M., & Pandarinath, C.
- Affiliations
- Georgia Institute of Technology (US)
- Northwestern University (US)
- University of California, Davis (US)
- Massachusetts General Hospital (US)
- Brown University (US)
- Harvard University (US)
- Corresponding author
- Pandarinath, Chethan
- ORCID
- Venue
- Journal of Neural Engineering
- Publisher
- IOP Publishing
- Published
- 2024-04-01
- Volume
- 21
- Issue
- 2
- Pages
- 026046
- ISSN
- 1741-2552 (ISSN-L)
- 1741-2560
- PMC
- PMC11021878
- OpenAlex
- W4393970686
- Cited by
- 32
- References
- 37
- Citations by year
- 2026: 13 · 2025: 15 · 2024: 3
- FWCI
- 7.51
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (vor, 16 d)
- iopscience.iop.org/info/page/text-and-data-mining (tdm, 16 d)
- Locations
- Journal of Neural Engineering (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- PubMed Central (submittedVersion)
- Funders
- Emory Neuromodulation and Technology Innovation Center
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (F32HD112173)
- National Institute on Deafness and Other Communication Disorders (DP2DC021055)
- Simons Foundation (872146SPI)
- Rehabilitation Research and Development Service (A2295R)
- National Institute of Neurological Disorders and Stroke (DP2NS127291)
- National Institute of Biomedical Imaging and Bioengineering (T32EB025816)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Engineering › Control and Systems Engineering › Embedded Systems and FPGA Design
- Social Sciences › Education › Undergraduate Neuroscience Education and Research
- Keywords
- brand, closed-loop experiments, real-time neural decoding, interprocess communication, Redis, brain-computer interface, cursor control, modular software architecture
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.