pith. sign in

arxiv: 2606.09120 · v1 · pith:USBNTN6Fnew · submitted 2026-06-08 · 💻 cs.DC

AutoPilot: Learning to Steer High Speed Robust BFT

Liangrong Chen , Yue Zhang , Eric Zhou , Mohammad Javad Amiri , Ryan Marcus , Chenyuan Wu This is my paper

Pith reviewed 2026-06-27 15:00 UTC · model grok-4.3

classification 💻 cs.DC
keywords Byzantine fault tolerancereinforcement learningdynamic parameter tuningconsensus protocolsdistributed systemsonline optimizationadversarial robustness
0
0 comments X

The pith

A decentralized reinforcement learning framework dynamically tunes parameters in high-speed BFT protocols to optimize performance under changing conditions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

High-speed BFT protocols achieve strong results by blending leader-based and DAG-based designs but rely on static configurations that lose effectiveness when workloads, networks, or adversaries shift. AutoPilot applies reinforcement learning to monitor conditions at runtime and adjust parameters online. The learning is coordinated across nodes in a decentralized fashion to stay resilient against polluted data from adversaries. When tested on Autobahn across varied dynamic settings, the approach converges rapidly and produces clear gains over fixed and random baselines.

Core claim

AutoPilot is a reinforcement learning-based framework that continuously monitors runtime conditions and dynamically adjusts protocol parameters online to optimize consensus performance. Coordinated in a decentralized manner to provide resilience against adversarial data pollution, when implemented on the Autobahn protocol it quickly converges to optimal configurations under changing environments, reduces end-to-end latency by 49.8 percent compared to the default protocol configuration, and outperforms random configuration exploration by 73.3 percent.

What carries the argument

Decentralized reinforcement learning framework that coordinates parameter tuning across nodes while resisting adversarial data pollution.

Load-bearing premise

Decentralized reinforcement learning can reliably converge to optimal parameters while remaining robust to adversarial data pollution and that the tested dynamic environments represent real deployment conditions.

What would settle it

Deploying the system on a live network with actual adversaries and measuring whether latency reductions and convergence hold or break would directly test the central claim.

Figures

Figures reproduced from arXiv: 2606.09120 by Chenyuan Wu, Eric Zhou, Liangrong Chen, Mohammad Javad Amiri, Ryan Marcus, Yue Zhang.

Figure 1
Figure 1. Figure 1: Example on Autobahn’s cuts. When cut condition is configured to 2𝑓 + 1, a cut will be created once every 3 new tips are generated. create the next header. A replica votes for another replica’s new header if and only if it has already voted for that header’s parent, a rule known as in-order voting. This mechanism ensures that the complete history of each lane is possessed by at least 𝑓 + 1 replicas and can … view at source ↗
Figure 2
Figure 2. Figure 2: Overview of learning process on replica 𝑖. formulation rather than full reinforcement learning for two rea￾sons. First, CMAB admits asymptotically optimal algorithms (e.g., Thompson Sampling [32]) with well-studied regret bounds [14], providing strong theoretical guarantees on convergence. Second, CMAB algorithms are significantly more sample-efficient than full reinforcement learning, which is critical in… view at source ↗
Figure 4
Figure 4. Figure 4: Adaptivity of AutoPilot under changing conditions. The vertical dashed lines indicate when environments change. [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Robustness of AutoPilot against data pollution [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
read the original abstract

Recent Byzantine Fault Tolerant (BFT) protocols achieve strong performance by combining the low-latency advantages of leader-based BFT protocols with the high-throughput benefits of DAG-based data dissemination. Despite exposing a wide spectrum of internal tunable parameters, these protocols typically rely on static and heuristic configurations, which leads to performance degradation under dynamic workloads, heterogeneous network conditions, and evolving adversarial behaviors. In this paper, we present AutoPilot, a reinforcement learning-based framework that continuously monitors runtime conditions and dynamically adjusts protocol parameters online to optimize consensus performance. To ensure robustness, AutoPilot coordinates learning in a decentralized manner, providing resilience against adversarial data pollution. We implement AutoPilot on top of Autobahn, a state-of-the-art, highspeed, robust BFT protocol, and evaluate it across diverse dynamic environments. Experimental results demonstrate that AutoPilot quickly converges to the optimal configuration under changing environments, reduces end-to-end latency by 49.8% compared to the default protocol configuration, and outperforms random configuration exploration by 73.3%.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 0 minor

Summary. The paper introduces AutoPilot, a reinforcement learning framework for online, dynamic adjustment of internal parameters in high-speed robust BFT protocols (implemented on Autobahn). It claims decentralized coordination enables resilience to adversarial data pollution, with experiments across dynamic environments showing quick convergence to optimal configurations, a 49.8% end-to-end latency reduction versus the default static configuration, and 73.3% better performance than random configuration exploration.

Significance. If the empirical results and robustness properties hold under scrutiny, the work would offer a practical advance for maintaining high performance in BFT systems facing heterogeneous networks, evolving workloads, and adversaries, reducing reliance on manual or heuristic tuning. The decentralized RL approach directly targets a key distributed-systems challenge.

major comments (3)
  1. [Abstract] Abstract: the headline empirical claims (49.8% latency reduction vs. default; 73.3% improvement over random) are presented without any description of experimental methodology, baselines, number of runs, statistical tests, or workload/adversary models, rendering it impossible to evaluate whether the data support the claims.
  2. [Abstract] Abstract: the central robustness claim—that decentralized coordination prevents adversarial data pollution—lacks any description of the state representation, reward function, update aggregation rule, or Byzantine-resilient mechanism (e.g., outlier filtering or resilient averaging); without these, the attribution of performance gains to the claimed property cannot be assessed.
  3. [Abstract] Abstract: no ablation isolating the decentralized learner from a centralized counterpart, and no experiments injecting targeted false gradients or polluted state reports, are referenced; these are load-bearing for the claim that coordination provides resilience.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the comments on the abstract. We agree that the abstract would benefit from additional context on methodology and mechanisms to support the claims, and we will revise it in the next version while preserving conciseness. Full details remain in the body of the paper.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the headline empirical claims (49.8% latency reduction vs. default; 73.3% improvement over random) are presented without any description of experimental methodology, baselines, number of runs, statistical tests, or workload/adversary models, rendering it impossible to evaluate whether the data support the claims.

    Authors: We agree the abstract is too terse on these points. In revision we will add a brief clause summarizing the experimental methodology, baselines (static defaults and random exploration), workloads, and evaluation approach from Section 5 so that the headline numbers can be assessed at a glance. revision: yes

  2. Referee: [Abstract] Abstract: the central robustness claim—that decentralized coordination prevents adversarial data pollution—lacks any description of the state representation, reward function, update aggregation rule, or Byzantine-resilient mechanism (e.g., outlier filtering or resilient averaging); without these, the attribution of performance gains to the claimed property cannot be assessed.

    Authors: The abstract currently gives only a high-level summary. We will expand it with one sentence outlining the decentralized RL components (state, reward, resilient aggregation) and the Byzantine-resilient mechanism, cross-referencing Sections 3 and 4 for the technical description. revision: yes

  3. Referee: [Abstract] Abstract: no ablation isolating the decentralized learner from a centralized counterpart, and no experiments injecting targeted false gradients or polluted state reports, are referenced; these are load-bearing for the claim that coordination provides resilience.

    Authors: We will add a short reference in the abstract to the ablation studies and adversarial-injection experiments that appear in Section 5, thereby linking the resilience claim to the supporting evidence already present in the manuscript. revision: yes

Circularity Check

0 steps flagged

No circularity; purely empirical claims with no derivations

full rationale

The paper presents an empirical RL-based framework for online BFT parameter tuning, with performance claims (latency reductions, convergence) resting on implementation and experiments across environments. No equations, first-principles derivations, fitted parameters renamed as predictions, or self-citation chains appear in the provided text. The abstract and description contain no load-bearing mathematical steps that could reduce to inputs by construction. This is the expected outcome for an applied systems paper whose central results are experimental rather than deductive.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no information on free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5716 in / 999 out tokens · 26271 ms · 2026-06-27T15:00:50.449993+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

90 extracted references · 6 canonical work pages

  1. [1]

    [n. d.]. Aptos. https://aptosnetwork.com/

  2. [2]

    [n. d.]. Autobahn Codebase. https://github.com/neilgiri/autobahn-artifact

  3. [3]

    [n. d.]. Avalanche. https://www.avax.network/

  4. [4]

    [n. d.]. Dalek elliptic curve cryptography. https://github.com/dalek- cryptography/curve25519-dalek/tree/main/ed25519-dalek

  5. [5]

    [n. d.]. Fantom. https://fantom.foundation/

  6. [6]

    [n. d.]. MicrosoftCCF. https://github.com/microsoft/CCF

  7. [7]

    [n. d.]. RocksDB, version 0.16.0. https://rocksdb.org/

  8. [8]

    [n. d.]. Sei Giga. https://docs.sei.io/learn/sei-giga

  9. [9]

    [n. d.]. Somnia. https://docs.somnia.network

  10. [10]

    [n. d.]. Stable. https://docs.stable.xyz/

  11. [11]

    [n. d.]. Sui. https://sui.io/

  12. [12]

    [n. d.]. Tokio, version 1.5.0. https://tokio.rs/

  13. [13]

    Atul Adya, William J Bolosky, Miguel Castro, Gerald Cermak, Ronnie Chaiken, John R Douceur, Jon Howell, Jacob R Lorch, Marvin Theimer, and Roger P Wattenhofer. 2002. 𝐹 𝐴𝑅𝑆𝐼𝑇 𝐸: Federated, Available, and Reliable Storage for an Incompletely Trusted Environment. InSymposium on Operating Systems Design and Implementation (OSDI). USENIX Association

    2002

  14. [14]

    Shipra Agrawal and Navin Goyal. 2013. Further Optimal Regret Bounds for Thompson Sampling. InThe International Conference on Artificial Intelligence and Statistics(2013)(AISTATS ’13)

    2013

  15. [15]

    Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, and Geovani Rizk. 2023. Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity. InConf. on Neural Information Processing Sys- tems (NeurIPS)

    2023

  16. [16]

    Yair Amir, Brian Coan, Jonathan Kirsch, and John Lane. 2011. Prime: Byzantine replication under attack.Transactions on Dependable and Secure Computing8, 4 (2011), 564–577

    2011

  17. [17]

    Mohammad Javad Amiri, Divyakant Agrawal, and Amr El Abbadi. 2019. CAPER: a cross-application permissioned blockchain.Proc. of the VLDB Endowment12, 11 (2019), 1385–1398

    2019

  18. [18]

    Mohammad Javad Amiri, Divyakant Agrawal, and Amr El Abbadi. 2021. SharPer: Sharding Permissioned Blockchains Over Network Clusters. InSIGMOD Int. Conf. on Management of Data. ACM, 76–88

    2021

  19. [19]

    Min An, Xuan Zhang, Jishu Wang, Qiyuan Fan, Chen Gao, Linyu Li, Cuizhen Lu, Nan Li, and Yingchen Liu. 2024. Rlchain: A drl approach for blockchain performance optimization toward iiot.IEEE Transactions on Network and Service Management22, 2 (2024), 1629–1645

    2024

  20. [20]

    Balaji Arun, Zekun Li, Florian Suri-Payer, Sourav Das, and Alexander Spiegel- man. 2025. Shoal++: High Throughput DAG BFT Can Be Fast and Robust!. In Symposium on Networked Systems Design and Implementation (NSDI). USENIX Association

    2025

  21. [21]

    Amy Babay, John Schultz, Thomas Tantillo, Samuel Beckley, Eamon Jordan, Kevin Ruddell, Kevin Jordan, and Yair Amir. 2019. Deploying intrusion-tolerant SCADA for the power grid. InInt. Conf. on Dependable Systems and Networks (DSN). IEEE, 328–335

    2019

  22. [22]

    Jean-Paul Bahsoun, Rachid Guerraoui, and Ali Shoker. 2015. Making BFT proto- cols really adaptive. InInt. Parallel and Distributed Processing Symposium. IEEE, 904–913

    2015

  23. [23]

    Gilad Baruch, Moran Baruch, and Yoav Goldberg. 2019. A little is enough: Circumventing defenses for distributed learning.Advances in Neural Information Processing Systems32 (2019)

    2019

  24. [24]

    Alysson Bessani, Miguel Correia, Bruno Quaresma, Fernando André, and Paulo Sousa. 2013. DepSky: dependable and secure storage in a cloud-of-clouds.Trans- actions on Storage (TOS)9, 4 (2013), 12

    2013

  25. [25]

    Leo Breiman. 1996. Bagging Predictors. InMachine Learning(1996)(Maching Learning ’96)

    1996

  26. [26]

    Leo Breiman. 2001. Random forests.Machine learning45 (2001), 5–32

    2001

  27. [27]

    Richard Gendal Brown, James Carlyle, Ian Grigg, and Mike Hearn. 2016. Corda: an introduction.R3 CEV, August1, 15 (2016), 14

    2016

  28. [28]

    Yehonatan Buchnik and Roy Friedman. 2020. FireLedger: a high throughput blockchain consensus protocol.Proceedings of the VLDB Endowment13, 9 (2020), 1525–1539

    2020

  29. [29]

    Miguel Castro and Barbara Liskov. 1999. Practical Byzantine fault tolerance. In Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association, 173–186

    1999

  30. [30]

    Miguel Castro and Barbara Liskov. 2002. Practical Byzantine fault tolerance and proactive recovery.Transactions on Computer Systems (TOCS)20, 4 (2002), 398–461

    2002

  31. [31]

    Jeeta Ann Chacko, Ruben Mayer, and Hans-Arno Jacobsen. 2023. How to optimize my blockchain? a multi-level recommendation approach. 1, 1 (2023), 1–27

    2023

  32. [32]

    Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of Thompson sampling. InAdvances in neural information processing systems(2011)(NIPS’11)

    2011

  33. [33]

    Feng Cheng, Jiang Xiao, Cunyang Liu, Shijie Zhang, Yifan Zhou, Bo Li, Baochun Li, and Hai Jin. 2024. Shardag: Scaling dag-based blockchains via adaptive sharding. InInt. Conf. on Data Engineering (ICDE). IEEE, 2068–2081

    2024

  34. [34]

    Allen Clement, Manos Kapritsos, Sangmin Lee, Yang Wang, Lorenzo Alvisi, Mike Dahlin, and Taylor Riche. 2009. Upright cluster services. InSymposium on Operating Systems Principles (SOSP). ACM, 277–290

    2009

  35. [35]

    Allen Clement, Edmund L Wong, Lorenzo Alvisi, Michael Dahlin, and Mirco Marchetti. 2009. Making Byzantine Fault Tolerant Systems Tolerate Byzantine Faults.. InSymposium on Networked Systems Design and Implementation (NSDI), Vol. 9. USENIX Association, 153–168

    2009

  36. [36]

    Xiaohai Dai, Wei Li, Guanxiong Wang, Jiang Xiao, Haoyang Chen, Shufei Li, Albert Y Zomaya, and Hai Jin. 2024. Remora: A low-latency dag-based bft through optimistic paths.Transactions on Computers(2024)

    2024

  37. [37]

    Xiaohai Dai, Guanxiong Wang, Jiang Xiao, Zhengxuan Guo, Rui Hao, Xia Xie, and Hai Jin. 2024. LightDAG: A low-latency DAG-based BFT consensus through lightweight broadcast. InInt. Parallel and Distributed Processing Symposium (IPDPS). IEEE, 998–1008

    2024

  38. [38]

    Xiaohai Dai, Zhaonan Zhang, Zhengxuan Guo, Chaozheng Ding, Jiang Xiao, Xia Xie, Rui Hao, and Hai Jin. 2024. Wahoo: A dag-based bft consensus with low latency and low communication overhead.Transactions on Information Forensics and Security(2024)

    2024

  39. [39]

    Xiaohai Dai, Zhaonan Zhang, Jiang Xiao, Jingtao Yue, Xia Xie, and Hai Jin. 2023. GradedDAG: An asynchronous DAG-based BFT consensus with lower latency. InInt. Symposium on Reliable Distributed Systems (SRDS). IEEE, 107–117

    2023

  40. [40]

    George Danezis, Lefteris Kokoris-Kogias, Alberto Sonnino, and Alexander Spiegelman. 2022. Narwhal and Tusk: a DAG-based mempool and efficient BFT consensus. InEuropean Conf. on Computer Systems (EuroSys). 34–50

    2022

  41. [41]

    Qiuyu Ding, Rongkai Zhang, Qinnan Zhang, Zhen Xiao, Jieyi Long, Mingchao Wan, Sen Liu, and Jin Dong. 2026. Alzo: Auto-Tuning with Reinforcement Learning for DAG-based Blockchains. InProceedings of the ACM Web Conference

    2026

  42. [42]

    Dan Dobre, Ghassan Karame, Wenting Li, Matthias Majuntke, Neeraj Suri, and Marko Vukolić. 2013. PoWerStore: Proofs of writing for efficient and robust storage. InConf. on Computer and communications security (CCS). ACM, 285–298

    2013

  43. [43]

    Cynthia Dwork, Nancy Lynch, and Larry Stockmeyer. 1988. Consensus in the presence of partial synchrony.Journal of the ACM (JACM)35, 2 (1988), 288–323

    1988

  44. [44]

    facebookresearch. 2026. Narwhal. https://github.com/facebookresearch/narwhal. Public code repository for Narwhal and Tusk

    2026

  45. [45]

    Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, and John Stephan. 2022. Byzantine machine learning made easy by resilient averaging of momentums. InInt. Conf. on Machine Learning (ICML). PMLR, 6246–6283

    2022

  46. [46]

    Miguel Garcia, Nuno Neves, and Alysson Bessani. 2016. SieveQ: A layered bft protection system for critical services.IEEE Transactions on Dependable and Secure Computing15, 3 (2016), 511–525

    2016

  47. [47]

    Neil Giridharan, Florian Suri-Payer, Ittai Abraham, Lorenzo Alvisi, and Natacha Crooks. 2024. Autobahn: Seamless high speed BFT. InSymposium on Operating Systems Principles (SOSP). ACM SIGOPS, 1–23

    2024

  48. [48]

    Garth R Goodson, Jay J Wylie, Gregory R Ganger, and Michael K Reiter. 2004. Efficient Byzantine-tolerant erasure-coded storage. InInt. Conf. on Dependable Systems and Networks (DSN). IEEE, 135–144

    2004

  49. [49]

    Christian Gorenflo, Stephen Lee, Lukasz Golab, and Srinivasan Keshav. 2019. Fastfabric: Scaling hyperledger fabric to 20,000 transactions per second. InInt. Conf. on Blockchain and Cryptocurrency (ICBC). IEEE, 455–463

    2019

  50. [50]

    Tenenbaum, and Tim Mattson

    Justin Gottschlich, Armando Solar-Lezama, Nesime Tatbul, Michael Carbin, Mar- tin Rinard, Regina Barzilay, Saman Amarasinghe, Joshua B. Tenenbaum, and Tim Mattson. 2018. The three pillars of machine programming. InProceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Program- ming Languages(Philadelphia, PA, USA, 2018-06-18)(MA...

    work page doi:10.1145/3211346.3211355 2018

  51. [51]

    Rachid Guerraoui, Sébastien Rouault, et al. 2018. The hidden vulnerability of distributed learning in byzantium. InInt. Conf. on Machine Learning (ICML). PMLR, 3521–3530

    2018

  52. [52]

    Guy Golan Gueta, Ittai Abraham, Shelly Grossman, Dahlia Malkhi, Benny Pinkas, Michael K Reiter, Dragos-Adrian Seredinschi, Orr Tamir, and Alin Tomescu. 2019. SBFT: a Scalable Decentralized Trust Infrastructure for Blockchains. InInt. Conf. on Dependable Systems and Networks (DSN). IEEE/IFIP, 568–580

    2019

  53. [53]

    Niranjan Hasabnis and Justin Gottschlich. 2021. ControlFlag: a self-supervised idiosyncratic pattern detection system for software control structures. InProceed- ings of the 5th ACM SIGPLAN International Symposium on Machine Programming (New York, NY, USA, 2021-06-20)(MAPS ’21). Association for Computing Ma- chinery, 32–42. doi:10.1145/3460945.3464954

    work page doi:10.1145/3460945.3464954 2021

  54. [54]

    HyperLedger. 2019. https://github.com/hyperledger/ursa

    2019

  55. [55]

    Dakai Kang, Junchao Chen, Tien Tuan Anh Dinh, and Mohammad Sadoghi. 2025. FairDAG: consensus fairness over multi-proposer causal design.Proceedings of the VLDB Endowment19, 2 (2025), 265–278

    2025

  56. [56]

    Dakai Kang, Suyash Gupta, Dahlia Malkhi, and Mohammad Sadoghi. 2025. Hotstuff-1: Linear consensus with one-phase speculation.Proceedings of the ACM on Management of Data3, 3 (2025), 1–29

    2025

  57. [57]

    Sai Praneeth Karimireddy, Lie He, and Martin Jaggi. 2021. Learning from history for byzantine robust optimization. InInt. Conf. on Machine Learning (ICML). PMLR, 5311–5319

    2021

  58. [58]

    Idit Keidar, Eleftherios Kokoris-Kogias, Oded Naor, and Alexander Spiegelman

  59. [59]

    InSymposium on Principles of Distributed Computing (PODC)

    All you need is dag. InSymposium on Principles of Distributed Computing (PODC). ACM, 165–175

  60. [60]

    Kieckhafer and Mohammad H

    Roger M. Kieckhafer and Mohammad H. Azadmanesh. 1994. Reaching approxi- mate agreement with mixed-mode faults.Transactions on Parallel and Distributed Systems5, 1 (1994), 53–63

    1994

  61. [61]

    Eleftherios Kokoris Kogias, Philipp Jovanovic, Nicolas Gailly, Ismail Khoffi, Linus Gasser, and Bryan Ford. 2016. Enhancing bitcoin security and performance with strong consistency via collective signing. InSecurity Symposium. USENIX Association, 279–296

    2016

  62. [62]

    Eleftherios Kokoris-Kogias, Philipp Jovanovic, Linus Gasser, Nicolas Gailly, Ewa Syta, and Bryan Ford. 2018. Omniledger: A secure, scale-out, decentralized ledger via sharding. InSymposium on Security and Privacy (SP). IEEE, 583–598

    2018

  63. [63]

    Ramakrishna Kotla, Lorenzo Alvisi, Mike Dahlin, Allen Clement, and Edmund Wong. 2007. Zyzzyva: speculative byzantine fault tolerance.Operating Systems Review (OSR)41, 6 (2007), 45–58

    2007

  64. [64]

    Chi, Jeffrey Dean, and Neoklis Polyzotis

    Tim Kraska, Alex Beutel, Ed H. Chi, Jeffrey Dean, and Neoklis Polyzotis. 2018. The Case for Learned Index Structures. InProceedings of the 2018 International Conference on Management of Data(New York, NY, USA, 2018)(SIGMOD ’18). ACM. doi:10.1145/3183713.3196909

    work page doi:10.1145/3183713.3196909 2018

  65. [65]

    Binhong Li, Licheng Lin, Shijie Zhang, Jianliang Xu, Jiang Xiao, Bo Li, and Hai Jin. 2025. FlexIM: efficient and verifiable index management in Blockchain.IEEE Transactions on Knowledge and Data Engineering(2025)

    2025

  66. [66]

    Mingxuan Li, Yazhe Wang, Shuai Ma, Chao Liu, Dongdong Huo, Yu Wang, and Zhen Xu. 2023. Auto-tuning with reinforcement learning for permissioned blockchain systems.Proceedings of the VLDB Endowment16, 5 (2023), 1000–1012

    2023

  67. [67]

    Loi Luu, Viswesh Narayanan, Chaodong Zheng, Kunal Baweja, Seth Gilbert, and Prateek Saxena. 2016. A secure sharding protocol for open blockchains. In SIGSAC Conf. on Computer and Communications Security (CCS). ACM, 17–30

    2016

  68. [68]

    Dahlia Malkhi and Michael K Reiter. 1998. Secure and scalable replication in Phalanx. InSymposium on Reliable Distributed Systems (SRDS). IEEE, 51–58

    1998

  69. [69]

    Dahlia Malkhi, Chrysoula Stathakopoulou, and Maofan Yin. 2024. BBCA-CHAIN: Low latency, high throughput BFT consensus on a DAG. InInt. Conf. on Financial Cryptography and Data Security (FC). Springer, 51–73

    2024

  70. [70]

    Hongzi Mao, Malte Schwarzkopf, Shaileshh Bojja Venkatakrishnan, Zili Meng, and Mohammad Alizadeh. 2018. Learning Scheduling Algorithms for Data Processing Clusters. (2018). arXiv:1810.01963 http://arxiv.org/abs/1810.01963

    arXiv 2018

  71. [71]

    Ryan Marcus, Parimarjan Negi, Hongzi Mao, Nesime Tatbul, Mohammad Al- izadeh, and Tim Kraska. 2021. Bao: Making Learned Query Optimization Practical. InProceedings of the 2021 International Conference on Management of Data(China, 2021-06)(SIGMOD ’21). doi:10.1145/3448016.3452838 Award: ’best paper award’

    work page doi:10.1145/3448016.3452838 2021

  72. [72]

    Heena Nagda, Sidharth Sankhe, Sakshi Sinha, Keon Attarha, Mohammad Javad Amiri, and Boon Thau Loo. 2026. DAG of DAGs: Order-Fairness Made Practical. InSIGMOD Int. Conf. on Management of Data. ACM

    2026

  73. [73]

    Ian Osband and Benjamin Van Roy. 2015. Bootstrapped Thompson Sampling and Deep Exploration. (2015). http://arxiv.org/abs/1507.00300

    Pith/arXiv arXiv 2015

  74. [74]

    Apache ResilientDB. [n. d.]. Global-Scale Sustainable Blockchain Fabric. https://resilientdb.incubator.apache.org/. ([n. d.])

  75. [75]

    Tom Roeder and Fred B Schneider. 2010. Proactive obfuscation.ACM Transactions on Computer Systems (TOCS)28, 2 (2010), 1–54

    2010

  76. [76]

    Nibesh Shrestha, Rohan Shrothrium, Aniket Kate, and Kartik Nayak. 2024. Sail- fish: Towards Improving the Latency of DAG-based BFT. InSymposium on Secu- rity and Privacy (SP). IEEE, 21–21

    2024

  77. [77]

    Paulo Sousa, Alysson Neves Bessani, Miguel Correia, Nuno Ferreira Neves, and Paulo Verissimo. 2009. Highly available intrusion-tolerant services with proactive-reactive recovery.IEEE Transactions on Parallel and Distributed Systems 21, 4 (2009), 452–465

    2009

  78. [78]

    Alexander Spiegelman, Balaji Arun, Rati Gelashvili, and Zekun Li. 2024. Shoal: Improving dag-bft latency and robustness. InInt. Conf. on Financial Cryptography and Data Security (FC). Springer, 92–109

    2024

  79. [79]

    Alexander Spiegelman, Neil Giridharan, Alberto Sonnino, and Lefteris Kokoris- Kogias. 2022. Bullshark: Dag bft protocols made practical. InACM SIGSAC Conf. on Computer and Communications Security (CCS). 2705–2718

    2022

  80. [80]

    Gordon, and Bohan Zhang

    Dana Van Aken, Andrew Pavlo, Geoffrey J. Gordon, and Bohan Zhang. 2017. Automatic Database Management System Tuning Through Large-scale Machine Learning. InProceedings of the 2017 ACM International Conference on Management of Data(New York, NY, USA, 2017)(SIGMOD ’17). ACM, 1009–1024. doi:10.1145/ 3035918.3064029

    arXiv 2017

Showing first 80 references.