pith. sign in

arxiv: 2605.20595 · v1 · pith:W6MOVRBPnew · submitted 2026-05-20 · 💻 cs.RO · cs.MA· cs.NI

Intent-First Aerial V2V for Tactical Coordination and Separation: Protocol and Performance Under Density and Disturbance

Mehrnaz Sabet This is my paper

Pith reviewed 2026-05-21 05:12 UTC · model grok-4.3

classification 💻 cs.RO cs.MAcs.NI
keywords V2V communicationtactical separationUTMaerial coordinationC-V2X sidelinkintent-first messagingdense airspaceunmanned aircraft systems
0
0 comments X

The pith

An intent-first V2V stack supports tactical separation for unmanned aircraft in lower-to-moderate density regimes but shifts to guarded fallback as density, impairment, and complexity rise.

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

This paper develops and tests an all-airborne vehicle-to-vehicle communication protocol tailored for tactical coordination among drones in dense low-altitude airspace. It fills the gap between pre-flight route planning and last-resort collision avoidance by exchanging refreshed state and intent information along with event-triggered messages for local actions. High-volume stress evaluations using field-anchored infrastructure show the approach cuts outdated beliefs, maintains cooperative perception, filters bad messages, and organizes shared resources effectively at moderate levels. A reader would care because growing drone operations in urban areas need reliable neighborhood coordination that responds faster than central systems yet avoids constant emergency maneuvers. The work shows this communication layer works as a practical enabler within clear limits.

Core claim

The paper claims that the implemented controller-coupled, intent-first V2V tactical neighborhood exchange stack using sidelink-class C-V2X modules with authenticated freshness checks reduces stale-belief divergence, preserves observability through cooperative perception, rejects invalid tactical messages, suppresses false local inference, and structures shared-resource coordination, thereby providing a viable communication layer for tactical separation in lower-to-moderate regimes while transitioning toward guarded fallback as density, impairment, and complexity increase.

What carries the argument

The intent-first V2V tactical neighborhood exchange stack that combines refreshed state and intent beacons for local awareness and cooperative perception with event-triggered messages for yielding, sequencing, release, and contingency coordination.

If this is right

  • V2V reduces stale-belief divergence among nearby aircraft.
  • It preserves observability through cooperative perception.
  • Invalid tactical messages are rejected and false local inferences are suppressed.
  • Shared-resource coordination is structured through event-triggered exchanges for yielding, sequencing, and contingencies.
  • The stack remains viable in lower-to-moderate regimes but shifts toward guarded fallback with rising density and disturbance.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This mechanism could extend to hybrid manned-unmanned coordination if adapted for compatibility with existing aviation protocols.
  • Further tests in uncontrolled outdoor environments would better reveal where the transition to fallback occurs in practice.
  • Integration with ground-based UTM services might allow hybrid local and central decision making for larger-scale operations.

Load-bearing premise

The results from the scenario-driven high-volume stress campaign supported by real-time field-anchored infrastructure generalize to real dense low-altitude aerial operations under disturbance.

What would settle it

Real-world flights at higher densities with actual disturbances that produce frequent stale beliefs, rejected messages, or heavy reliance on fallbacks would show the viability claim does not hold beyond moderate regimes.

Figures

Figures reproduced from arXiv: 2605.20595 by Mehrnaz Sabet.

Figure 1
Figure 1. Figure 1: Real-time field-anchored evaluation infrastructure. Left: physical multi-drone field operation. Upper right: corresponding field-synchronized real-time simulation view of the 1:1 urban operating environment. Lower right: hybrid operation coupling live hardware nodes with real-time simulated traffic, urban context, and scenario constraints. The stack exercises operational complexity around physical flight i… view at source ↗
read the original abstract

Dense low-altitude aerial operations require more than pre-flight route coordination and last-resort collision avoidance. Once aircraft are airborne, disturbances can emerge on timescales shorter than strategic reauthorization can absorb, while collision avoidance is too late and disruptive to serve as routine traffic management. Although tactical separation is recognized as the intermediate layer, realizing it at scale requires a deployable neighborhood communication mechanism that provides fresh, trusted information for local coordination. This paper presents what is, to our knowledge, the first controller-coupled characterization of an all-airborne, sidelink-class, intent-first vehicle-to-vehicle (V2V) tactical neighborhood exchange stack for dense Unmanned Aircraft System Traffic Management (UTM) operations. Unlike awareness-only broadcast, the proposed exchange combines refreshed state and intent beacons for local awareness, cooperative perception, and degraded-mode assessment with event-triggered messages for yielding, sequencing, release, and contingency coordination. We implement and evaluate this model on an all-airborne V2V stack using sidelink-class C-V2X modules with authenticated freshness checks. Evaluation uses a scenario-driven, high-volume stress campaign supported by real-time, field-anchored infrastructure. Results show that V2V reduces stale-belief divergence, preserves observability through cooperative perception, rejects invalid tactical messages, suppresses false local inference, and structures shared-resource coordination. The implemented stack provides a viable communication layer for tactical separation in lower-to-moderate regimes, but transitions toward guarded fallback as density, impairment, and complexity increase. These findings position intent-first aerial V2V as a bounded enabler for scaling tactical coordination in disturbance-driven urban airspace.

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

2 major / 2 minor

Summary. The manuscript presents the first controller-coupled characterization of an all-airborne, sidelink-class, intent-first V2V tactical neighborhood exchange stack for dense UTM operations. The protocol combines refreshed state and intent beacons for local awareness and cooperative perception with event-triggered messages for yielding, sequencing, release, and contingency coordination. It is implemented on sidelink-class C-V2X modules with authenticated freshness checks and evaluated via a scenario-driven high-volume stress campaign supported by real-time, field-anchored infrastructure. Results indicate that the stack reduces stale-belief divergence, preserves observability, rejects invalid tactical messages, suppresses false local inference, and structures shared-resource coordination, providing a viable communication layer for tactical separation in lower-to-moderate regimes while transitioning toward guarded fallback as density, impairment, and complexity increase.

Significance. If the reported performance holds under detailed scrutiny, the work offers a practical contribution to aerial robotics and UTM by supplying a deployable neighborhood communication mechanism that operates on timescales between strategic reauthorization and last-resort collision avoidance. Explicit credit is due for the real-hardware implementation on C-V2X modules, the inclusion of authenticated freshness checks, and the use of field-anchored infrastructure to support high-volume stress testing; these elements strengthen the empirical grounding relative to purely simulated studies.

major comments (2)
  1. [Evaluation] Evaluation section: the central viability claim for lower-to-moderate regimes rests on results from the scenario-driven stress campaign, yet the manuscript supplies no quantitative metrics, error bars, baseline comparisons, or detailed exclusion criteria for the tested densities and impairment levels. Without these data the magnitude of reductions in stale-belief divergence or gains in observability preservation cannot be assessed, weakening support for the headline finding.
  2. [Evaluation] Evaluation / stress-campaign description: no quantitative mapping is provided between the modeled disturbance parameters (density ramps, impairment levels) and empirical distributions drawn from real urban low-altitude flight data, nor is a sensitivity analysis reported for metrics such as stale-belief divergence or false-inference suppression under plausible deviations (e.g., correlated gusts or regulatory handoffs). This omission directly affects whether the observed transition to guarded fallback can be treated as a robust protocol property rather than a testbed artifact.
minor comments (2)
  1. [Abstract] Abstract: the phrase 'to our knowledge, the first' would benefit from a concise sentence contrasting the proposed stack with prior awareness-only broadcast or UTM communication approaches to clarify the precise novelty.
  2. [Throughout] Notation and terminology: ensure consistent definition of acronyms (C-V2X, UTM, V2V) on first use and verify that all performance metrics referenced in the results are defined before they appear in the evaluation narrative.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and for acknowledging the practical contributions of the real-hardware C-V2X implementation and field-anchored stress testing. We address the two major comments on the Evaluation section point by point below. We will revise the manuscript to incorporate additional quantitative details and analyses as described.

read point-by-point responses

  1. Referee: [Evaluation] Evaluation section: the central viability claim for lower-to-moderate regimes rests on results from the scenario-driven stress campaign, yet the manuscript supplies no quantitative metrics, error bars, baseline comparisons, or detailed exclusion criteria for the tested densities and impairment levels. Without these data the magnitude of reductions in stale-belief divergence or gains in observability preservation cannot be assessed, weakening support for the headline finding.

    Authors: We agree that the current manuscript presents results primarily through descriptive trends without explicit numerical metrics, error bars, or direct baseline comparisons. In the revised version we will expand the Evaluation section to report specific quantitative values, including measured reductions in stale-belief divergence (with means and standard deviations across runs), observability preservation percentages, and false-inference suppression rates. We will add comparisons against a baseline awareness-only C-V2X broadcast protocol and will explicitly state the exclusion criteria applied to the stress-campaign scenarios, such as the density range (e.g., 5–25 aircraft/km²) and impairment thresholds used. These additions will allow readers to assess the magnitude of the reported effects. revision: yes

  2. Referee: [Evaluation] Evaluation / stress-campaign description: no quantitative mapping is provided between the modeled disturbance parameters (density ramps, impairment levels) and empirical distributions drawn from real urban low-altitude flight data, nor is a sensitivity analysis reported for metrics such as stale-belief divergence or false-inference suppression under plausible deviations (e.g., correlated gusts or regulatory handoffs). This omission directly affects whether the observed transition to guarded fallback can be treated as a robust protocol property rather than a testbed artifact.

    Authors: We concur that explicit mapping to real-world distributions and sensitivity analysis would strengthen claims of robustness. The revised manuscript will include a dedicated subsection that quantitatively maps the modeled density ramps and impairment levels to available empirical statistics from public urban low-altitude flight datasets and UTM testbed records. We will also add sensitivity results for stale-belief divergence and false-inference suppression under perturbations such as correlated gusts and simulated regulatory handoffs. Where comprehensive real-world traces for every deviation are unavailable, we will clearly state this limitation and rely on the field-anchored infrastructure data already collected; the transition to guarded fallback will be presented with these caveats rather than as an unqualified protocol property. revision: partial

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper presents an implementation of an intent-first V2V protocol and reports empirical results from a scenario-driven stress campaign using field-anchored infrastructure. No mathematical derivations, equations, fitted parameters, or predictions appear in the provided text. Claims about performance (stale-belief reduction, observability preservation, etc.) are grounded directly in the described evaluation campaign rather than reducing to self-definitions, self-citations, or ansatzes. The work is self-contained as an engineering evaluation without load-bearing theoretical steps that could introduce circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are identifiable from the abstract; the work applies existing C-V2X sidelink technology with added freshness and authentication checks rather than introducing new fundamental constructs.

pith-pipeline@v0.9.0 · 5827 in / 1236 out tokens · 75827 ms · 2026-05-21T05:12:17.521717+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

35 extracted references · 35 canonical work pages

  1. [1]

    is there a link?

    (a) Neighborhood PRR and (b) latency p95 across density and impairment class. PRR is measured as effective neighborhood reception under continuous multi-node broadcast. The 250 vehicles/km² slice is included as a diagnostic breakdown stress point. Deadline-miss behavior shows the transition more sharply. Deadline misses remain effectively zero under nomin...

    work page 1960

  2. [2]

    Available: https://ntrs.nasa.gov/citations/20205002076

    [Online]. Available: https://ntrs.nasa.gov/citations/20205002076

    work page arXiv

  3. [3]

    UAS traffic management communications: The legacy of ADS-B, new establishment of Remote ID, or leverage of ADS-B-like systems?,

    M. R. Jamali et al., "UAS traffic management communications: The legacy of ADS-B, new establishment of Remote ID, or leverage of ADS-B-like systems?," Drones, vol. 6, no. 3, Art. no. 57, 2022, doi: 10.3390/drones6030057

    work page doi:10.3390/drones6030057 2022

  4. [4]

    Reducing safe UAV separation distances with U2U communication and new Remote ID formats,

    E. Vinogradov, F. Minucci, A. V. S. S. B. Kumar, S. Pollin, and E. Natalizio, "Reducing safe UAV separation distances with U2U communication and new Remote ID formats," 2022, arXiv:2209.13270

    work page arXiv 2022

  5. [5]

    Remote ID for separation provision and multi-agent navigation,

    E. Vinogradov, A. V. S. S. B. Kumar, F. Minucci, S. Pollin, and E. Natalizio, "Remote ID for separation provision and multi-agent navigation," 2023, arXiv:2309.00843

    work page arXiv 2023

  6. [6]

    Markov decision process-based distributed conflict resolution for drone air traffic management,

    H. Y. Ong and M. J. Kochenderfer, "Markov decision process-based distributed conflict resolution for drone air traffic management," J. Guid., Control, Dyn., vol. 40, no. 1, pp. 69–80, Jan. 2017, doi: 10.2514/1.G001822

    work page doi:10.2514/1.g001822 2017

  7. [7]

    Game-theoretical approach to decentralized multi-drone conflict resolution and emergent traffic flow operations,

    S. Hoogendoorn, V. L. Knoop, H. Mahmassani, and S. Hoogendoorn-Lanser, "Game-theoretical approach to decentralized multi-drone conflict resolution and emergent traffic flow operations," 2023, arXiv:2308.01069

    work page arXiv 2023

  8. [8]

    MADER: Trajectory planner in multiagent and dynamic environments,

    J. Tordesillas and J. P. How, "MADER: Trajectory planner in multiagent and dynamic environments," IEEE Trans. Robot., vol. 38, no. 1, pp. 463–476, Feb. 2022, doi: 10.1109/TRO.2021.3080235

    work page doi:10.1109/tro.2021.3080235 2022

  9. [9]

    Robust MADER: Decentralized multiagent trajectory planner robust to communication delay in dynamic environments,

    K. Kondo et al., "Robust MADER: Decentralized multiagent trajectory planner robust to communication delay in dynamic environments," IEEE Robot. Autom. Lett., vol. 8, no. 3, pp. 1687–1694, Mar. 2023, doi: 10.1109/LRA.2023.3236923

    work page doi:10.1109/lra.2023.3236923 2023

  10. [10]

    Latency analysis of drone-assisted C-V2X communications for basic safety and cooperative perception messages,

    A. M. Khasawneh et al., "Latency analysis of drone-assisted C-V2X communications for basic safety and cooperative perception messages," Drones, vol. 8, no. 10, Art. no. 600, 2024, doi: 10.3390/drones8100600

    work page doi:10.3390/drones8100600 2024

  11. [11]

    V2X communication between connected and automated vehicles (CAVs) and unmanned aerial vehicles (UAVs),

    D. Kavas-Torris, S. Y. Gelbal, M. R. Cantas, B. Aksun-Guvenc, and L. Guvenc, "V2X communication between connected and automated vehicles (CAVs) and unmanned aerial vehicles (UAVs)," Sensors, vol. 22, no. 22, Art. no. 8941, 2022, doi: 10.3390/s22228941

    work page doi:10.3390/s22228941 2022

  12. [12]

    V2V UAS communications and use cases for advanced air mobility,

    G. Gür et al., "V2V UAS communications and use cases for advanced air mobility," in Proc. IEEE Conf. Standards Commun. Netw. (CSCN), 2024, pp. 103–107

    work page 2024

  13. [13]

    The philosophy of UAS-to-UAS communications,

    K. Namuduri, J. S. Mandapaka, and M. F. Kidane, "The philosophy of UAS-to-UAS communications," in Proc. MOBILITY 2024: 14th Int. Conf. Mobile Services, Resour. Users, 2024, pp. 1–6

    work page 2024

  14. [14]

    Digital traffic lights: UAS collision avoidance strategy for advanced air mobility,

    Z. McCorkendale, L. McCorkendale, and K. Namuduri, "Digital traffic lights: UAS collision avoidance strategy for advanced air mobility," Drones, vol. 8, no. 10, Art. no. 590, 2024, doi: 10.3390/drones8100590

    work page doi:10.3390/drones8100590 2024

  15. [15]

    Collision avoidance strategies for cooperative unmanned aircraft systems using vehicle-to-vehicle communications,

    J. S. Mandapaka, B. Dalloul, S. Hawkins, K. Namuduri, S. Nicoll, and K. Gambold, "Collision avoidance strategies for cooperative unmanned aircraft systems using vehicle-to-vehicle communications," in Proc. IEEE 97th Veh. Technol. Conf. (VTC2023-Spring), Florence, Italy, Jun. 2023, pp. 1–7, doi: 10.1109/VTC2023-Spring57618.2023.10199913

    work page doi:10.1109/vtc2023-spring57618.2023.10199913 2023

  16. [16]

    Collision avoidance strategies for advanced air mobility using UAS-to-UAS communications,

    J. S. Mandapaka, L. McCorkendale, Z. McCorkendale, and K. Namuduri, "Collision avoidance strategies for advanced air mobility using UAS-to-UAS communications," Drone Syst. Appl., vol. 13, 2025, doi: 10.1139/dsa-2024-0044

    work page doi:10.1139/dsa-2024-0044 2025

  17. [17]

    Available: https://www.rtca.org/wp-content/uploads/2023/01/V2V-White-Paper-Final.pdf

    [Online]. Available: https://www.rtca.org/wp-content/uploads/2023/01/V2V-White-Paper-Final.pdf

    work page 2023

  18. [18]

    Flight demonstration of unmanned aircraft system (UAS) traffic management (UTM) at technical capability level 3,

    A. Aweiss et al., "Flight demonstration of unmanned aircraft system (UAS) traffic management (UTM) at technical capability level 3," in Proc. IEEE/AIAA 38th Digit. Avion. Syst. Conf. (DASC), San Diego, CA, USA, Sep. 2019, pp. 1–7, doi: 10.1109/DASC43569.2019.9081718

    work page doi:10.1109/dasc43569.2019.9081718 2019

  19. [19]

    Vehicle to vehicle (V2V) communication for collision avoidance for multi-copters flying in UTM-TCL4,

    A. Chakrabarty, C. A. Ippolito, J. Baculi, K. S. Krishnakumar, and S. Hening, "Vehicle to vehicle (V2V) communication for collision avoidance for multi-copters flying in UTM-TCL4," in Proc. AIAA Scitech Forum, San Diego, CA, USA, Jan. 2019, doi: 10.2514/6.2019-0690

    work page doi:10.2514/6.2019-0690 2019

  20. [20]

    Full-duplex aerial communication system for multiple UAVs with directional antennas,

    T. Yu, K. Araki, and K. Sakaguchi, "Full-duplex aerial communication system for multiple UAVs with directional antennas," 2022, arXiv:2202.00176

    work page arXiv 2022

  21. [21]

    Air-to-air channel characterization for UAV communications at 3.4 GHz,

    A. Gürses, J. Kesler, and M. L. Sichitiu, "Air-to-air channel characterization for UAV communications at 3.4 GHz," 2026, arXiv:2604.01582

    work page arXiv 2026

  22. [22]

    Enhancing situational awareness in ISAC networks via drone swarms: A real-world channel sounding data set,

    J. Beuster et al., "Enhancing situational awareness in ISAC networks via drone swarms: A real-world channel sounding data set," in Proc. 28th Int. Workshop Smart Antennas (WSA), 2025, pp. 170–173

    work page 2025

  23. [23]

    Vehicle-to-vehicle based autonomous flight coordination control system for safer operation of unmanned aerial 14 vehicles,

    T.-W. Hsu et al., "Vehicle-to-vehicle based autonomous flight coordination control system for safer operation of unmanned aerial 14 vehicles," Drones, vol. 7, no. 11, Art. no. 669, 2023, doi: 10.3390/drones7110669

    work page doi:10.3390/drones7110669 2023

  24. [24]

    V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer,

    R. Xu et al., "V2X-ViT: Vehicle-to-everything cooperative perception with vision transformer," in Proc. Eur. Conf. Comput. Vis. (ECCV), Tel Aviv, Israel, 2022, pp. 107–124

    work page 2022

  25. [25]

    In: 2022 International Conference on Robotics and Automation (ICRA), pp

    R. Xu et al., "OPV2V: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication," in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Philadelphia, PA, USA, 2022, pp. 2583–2589, doi: 10.1109/ICRA46639.2022.9812038

    work page doi:10.1109/icra46639.2022.9812038 2022

  26. [26]

    CoMamba: Real-time cooperative perception unlocked with state space models,

    J. Zhao et al., "CoMamba: Real-time cooperative perception unlocked with state space models," 2024, arXiv:2409.10699

    work page arXiv 2024

  27. [27]

    CoFormerNet: A transformer-based fusion approach for enhanced vehicle-infrastructure cooperative perception,

    Y. Wang et al., "CoFormerNet: A transformer-based fusion approach for enhanced vehicle-infrastructure cooperative perception," Sensors, vol. 24, no. 13, Art. no. 4101, 2024, doi: 10.3390/s24134101

    work page doi:10.3390/s24134101 2024

  28. [28]

    MCOP: Multi-UAV collaborative occupancy prediction,

    Q. Wei et al., "MCOP: Multi-UAV collaborative occupancy prediction," 2025, arXiv:2510.12679

    work page arXiv 2025

  29. [29]

    AGC-Drive: A large-scale dataset for real-world aerial-ground collaboration in driving scenarios,

    L. Hou et al., "AGC-Drive: A large-scale dataset for real-world aerial-ground collaboration in driving scenarios," 2025, arXiv:2506.16371

    work page arXiv 2025

  30. [30]

    AirV2X: Unified air-ground vehicle-to-everything collaboration,

    X. Gao et al., "AirV2X: Unified air-ground vehicle-to-everything collaboration," 2025, arXiv:2506.19283

    work page arXiv 2025

  31. [31]

    IEEE standard for wireless access in vehicular environments — Security services for applications and management messages,

    IEEE, "IEEE standard for wireless access in vehicular environments — Security services for applications and management messages," IEEE Std 1609.2-2022, Piscataway, NJ, USA,

    work page 2022

  32. [32]

    Certificate management interfaces for end entities,

    IEEE, "Certificate management interfaces for end entities," IEEE Std 1609.2.1-2022, Piscataway, NJ, USA,

    work page 2022

  33. [33]

    Platoon control of connected multi-vehicle systems under V2X communications: Design and experiments,

    Y. Li, W. Chen, S. Peeta, and Y. Wang, "Platoon control of connected multi-vehicle systems under V2X communications: Design and experiments," IEEE Trans. Intell. Transp. Syst., vol. 21, no. 5, pp. 1891–1902, May 2020, doi: 10.1109/TITS.2019.2905039

    work page doi:10.1109/tits.2019.2905039 1902

  34. [34]

    Multivehicle cooperative driving using cooperative perception: Design and experimental validation,

    S.-W. Kim et al., "Multivehicle cooperative driving using cooperative perception: Design and experimental validation," IEEE Trans. Intell. Transp. Syst., vol. 16, no. 2, pp. 663–680, Apr. 2015, doi: 10.1109/TITS.2014.2352853

    work page doi:10.1109/tits.2014.2352853 2015

  35. [35]

    The upper bounds of cellular vehicle-to-vehicle communication latency for platoon-based autonomous driving,

    X. Chen, S. Leng, J. He, L. Zhou, and H. Liu, "The upper bounds of cellular vehicle-to-vehicle communication latency for platoon-based autonomous driving," IEEE Trans. Intell. Transp. Syst., vol. 24, no. 7, pp. 6874–6887, Jul. 2023, doi: 10.1109/TITS.2023.3284574. Mehrnaz Sabet is a Ph.D. candidate in the College of Computing and Information Science at Co...

    work page doi:10.1109/tits.2023.3284574 2023