---
title: 'SANDMAN: Multi-Domain Research Applications'
url: https://www.emergentmind.com/topics/sandman
type: topic
---

# SANDMAN: Multi-Domain Research Applications

Searching arXiv for recent papers on "SANDMAN" to ground the article and disambiguate the topic.
The published literature suggests that **SANDMAN** is not a single unified construct but a reused research label applied to several technically distinct systems. Its most prominent uses are as a practical algorithm for joint jammer mitigation and data detection in multi-user MIMO uplink communications, as an LLM-based Deceptive Agent architecture for cyber defense, as an execution-phase framework for measuring personality-driven task selection in autonomous agents, and, in an explicitly interpretive environmental-science usage, as a framework for realistic dune-field surface-stress prediction based on a mixing-layer analogy [2211.07211] [2503.19752] [2504.00727] [2004.05136].

## 1. Terminological scope and disciplinary uses

The term has been used across unrelated domains with different technical meanings. In the communications literature, **SANDMAN** is expanded as **SimultANeous Detection and MitigAtioN** and denotes a low-complexity instantiation of joint jammer mitigation and data detection. In cyber defense, it denotes an architecture of **Deceptive Agents** built from LLMs and conditioned by induced OCEAN traits. In a separate, interpretive environmental-science synthesis, it denotes a framework for predicting surface shear stress over realistic dune fields.

| Usage | Domain | Defining elements |
|---|---|---|
| SANDMAN | MU-MIMO uplink | SimultANeous Detection and MitigAtioN |
| SANDMAN | Cyber deception | LLM-based Deceptive Agent architecture |
| SANDMAN | Autonomous-agent decision-making | Personality-driven task selection and prioritization |
| SANDMAN | Aeolian morphodynamics | Mixing-layer-based surface-stress prediction |

A plausible source of confusion is the adjacency of the label to **SAND** detector literature. The DUNE near-detector study concerns the permanently on-axis **SAND** detector and its sensitivity to Heavy Neutral Leptons, rather than a system named SANDMAN; the overlap is terminological rather than substantive [2209.01899].

## 2. SANDMAN in joint jammer mitigation and data detection

In wireless communications, SANDMAN is a practical algorithm within the **joint jammer mitigation and data detection (JMD)** paradigm for the multi-user MIMO uplink. The system model assumes a base station with \(B\) antennas, \(U\) single-antenna user equipments, and a jammer, or multiple distributed jammers, with \(I\) total antennas. Over a coherence interval of \(K\) channel uses, partitioned into \(U\) pilot symbols and \(D\) data symbols, the per-slot received signal is
\[
y_k = H s_k + J w_k + n_k,
\]
where \(H \in \mathbb{C}^{B\times U}\) is the static MU-MIMO channel, \(s_k \in S^U\) are QPSK data or pilot symbols, \(J \in \mathbb{C}^{B\times I}\) is the receive-channel matrix from the jammer or jammers to the base station, \(w_k \in \mathbb{C}^{I}\) is the jammer transmit vector, and \(n_k \sim \mathcal{CN}(0,N_0 I_B)\) is AWGN. For dynamic multi-antenna jammers,
\[
w_k = A_k \tilde w_k,
\]
with \(\tilde w_k \sim \mathcal{CN}(0,I_I)\) and \(A_k \in \mathbb{C}^{I\times I}\) allowed to depend arbitrarily on \(k\), while \(\mathrm{col}(J A_k) \subseteq \mathrm{col}(J)\) for all \(k\), so the instantaneous jammer interference remains within the time-invariant subspace \(\mathrm{col}(J)\) over the coherence interval [2211.07211].

The central claim of JMD is that the jammer subspace can be estimated and removed **jointly** with data detection over the coherence interval, without a dedicated jammer training period. The resulting practical objective, using an LS channel estimate \(\hat H = Y_T S_T^\dagger\), is
\[
\min_{\hat S_D \in S^{U\times D},\ \tilde P \in \mathcal{G}_{B-I}(\mathbb{C}^B)}
\left\| \tilde P \left(Y_D - \hat H \hat S_D\right) \right\|_F^2.
\]
The key mechanism is that the pilot-contamination term in \(\hat H\) remains confined to \(\mathrm{col}(J)\), so with the true projector
\[
P = I_B - J J^\dagger,
\]
one has \(PJ=0\), \(P y_k = P H s_k + P n_k\), and \(P \hat H = P H\). Traditional training-based mitigation is therefore vulnerable in precisely the cases SANDMAN targets: jammers that are quiet during the training phase, jammers that vary their transmit beamforming over time, and multiple distributed single-antenna jammers whose aggregate interference is higher rank and harder to estimate from a dedicated training segment. The paper states the usual identifiability conditions in implicit form: \(I < B\), \(\mathrm{rank}(PH)=U\) or sufficiently well conditioned, and SNR/SJR regimes in which noise or residual modeling errors do not dominate [2211.07211].

## 3. Algorithmic structure, guarantees, and empirical behavior in communications

SANDMAN relaxes the discrete constellation constraint by replacing \(S\) with its convex hull \(C=\mathrm{conv}(S)\) and adding a concave regularizer:
\[
\min_{\hat S_D \in C^{U\times D},\ \tilde P \in \mathcal{G}_{B-I}(\mathbb{C}^B)}
\left\| \tilde P \left(Y_D - \hat H \hat S_D\right) \right\|_F^2 - \alpha \|\hat S_D\|_F^2.
\]
For fixed \(\tilde P\), the objective is convex in \(\hat S_D\) if \(\alpha \le \lambda_{\min}((\tilde P \hat H)^H (\tilde P \hat H))\). For fixed \(\hat S_D\), the optimal projector is
\[
\tilde P = I_B - U_I U_I^H,
\]
where \(U_I\) contains the \(I\) dominant left singular vectors of the residual. SANDMAN therefore alternates between a convex proximal-gradient update in \(\hat S_D\) and a subspace update via dominant left singular vectors. Its per-interval loop uses the residual
\[
E^{(t)} = [Y_T, Y_D] - \hat H [S_T,\hat S^{(t)}],
\]
updates the jammer subspace by approximate SVD, and applies forward-backward splitting with
\[
\nabla f(\hat S) = -2 \hat H^H \tilde P^{(t)}(Y_D - \hat H \hat S).
\]
The entrywise proximal map clips to the QPSK box when \(\tau \alpha < 1\) and projects to the nearest QPSK corner when \(\tau \alpha \ge 1\). The stated complexity is \(O(t_{\max} U D B)\), with approximate SVD contributing a modest \(O(I B (U+D))\) factor, and the projector need not be formed explicitly because \(\tilde P v\) can be applied as \(v-U_I(U_I^H v)\) [2211.07211].

The performance claims are framed around robustness to smart, distributed, and dynamic jammers. Against a strong single-antenna barrage jammer **30 dB stronger than the average UE**, SANDMAN achieves **MER \(\le 17.5\%\)** at essentially the same SNR as an oracle method, with **\(\approx 0.1\) dB difference**, while preserving **rate \(r=1\)** because it requires no jammer training period. A training-based baseline needs to sacrifice **\(\approx 20\%\)** of the coherence interval, or **\(r \approx 0.8\)**, to come within **\(\approx 0.5\) dB** of SANDMAN and still never surpasses it. Under data-only, pilot-only, or barrage jamming by a smart single-antenna jammer, SANDMAN’s BER versus SNR closely matches oracle bounds. For **four independent distributed barrage jammers**, each **24 dB stronger than average UE**, BER remains very close to oracle bounds. For **dynamic 4-antenna jammers** with jump-varying or continuously varying beamforming, SANDMAN maintains **BER \(\ll 1\%\)** at high SNR, with residual error floors slightly above **0.1%** under extremely rapid subspace changes [2211.07211].

A later JMD treatment formalizes an important failure mode, **eclipsing**, in which an incorrect data matrix can combine with jammer interference so that the projection nulls both. In the noise-free, non-eclipsed regime, the JMD solution is unique and recovers \(\hat P = I_B - J J^\dagger\) and \(\hat S_D = S_D\). The later paper also states that randomized pilots are essential when channel estimation is pilot-based, because if the jammer knows the pilots and jams pilots and data, it can eclipse with probability \(1-4^{-D}\approx 1\), whereas with unknown randomized pilots the eclipsing probability decays exponentially with the number of jammed symbols in the single-antenna case. That paper retains **SANDMAN** as the low-complexity JMD-type algorithm and contrasts it with the heavier **MAED** formulation that jointly estimates the effective channel, data, and projector [2510.02021].

## 4. SANDMAN as an LLM-based cyber-deception architecture

In cyber defense, SANDMAN is an architecture that operationalizes LLMs into **Deceptive Agents** designed to emulate convincing human simulacra in decoy environments. Its defensive objective is to mislead and slow adversaries while extending the observation window for early-stage attacker behaviors. The threat model is centered on unauthorized observers interacting with systems and data associated with simulated personas, and the architecture aims to prolong engagement by maintaining the illusion of a genuine, busy user whose behavior is consistent over time. The emphasis is on richer telemetry than that obtainable from static honeypots, including signals relevant to reconnaissance, lateral-movement precursors, credential harvesting, and social-engineering probes [2503.19752].

The architecture is modular. Its components are an **Agent Profile** that acts as semantic memory and encodes identity, role, occupation, passions, and induced personality; a **Decision Engine** that integrates memories, plans, task lists, generators, and channels; a unified **Memory** supporting semantic, episodic, procedural, and working memory; a **Task List with Bootstrap Task (PlanScheduleTask)** containing work and non-work tasks such as Call, Coffee, Email, Exercise, Reading, Lunch, Meeting, Break, Personal Time, Plan, Reflect, Research, Media, Collaboration/Teamwork, and Work; **Channels** that connect tasks to applications such as Firefox through a WebChannel or Microsoft Word through a document-authoring channel with human-like typing cadence and occasional mistakes; and **Generators** that use the LLM to produce task-specific textual content. The experiments also record generated schedules, positional features, durations, frequencies, and rejection counts, which constitute the measurement dataset [2503.19752].

The core behavioral mechanism is **prompt-based personality induction** through the Five-Factor Model, or **OCEAN**. The prompt schema is
> “Imagine you are a/an X person characterised by being Y”

where \(X\) is the Big Five trait label and \(Y\) is a descriptive word set associated with that trait. The paper gives concrete examples such as **Extraversion (+)** with “outgoing, energetic, public,” **Conscientiousness (+)** with “organized, reliable, disciplined,” and mirrored negative induction with antonymic words. In the reported experiments, SANDMAN uses **GPT-3.5-Turbo** at **Temperature = 0.7** for both MPI trials and schedule generation. To reduce deterministic bias from the order of the task list, the architecture applies **uniform randomization of the task list** and a **system message (Sys)**; the combined intervention reduces correlation between input list order and output schedule positions [2503.19752].

## 5. Personality induction, agenda generation, and execution-phase decision-making

The initial empirical program studies **agenda generation** as LLM-based planning of a daily routine. The Bootstrap Task prompts the model with the agent profile, relevant memory, the randomized Task List, and the Sys message, and returns a plausible daily schedule consisting of task assignments and durations. Validation proceeds through the **Machine Personality Inventory (MPI)**, with each persona prompt passed through the MPI five times, means and standard deviations computed per trait, and two-sample \(t\)-tests with significance threshold \(p \le 0.05\). The paper reports that each induced OCEAN trait, in both positive and negative form, produced statistically significant scores for the targeted trait relative to a neutral control, although **bleed-through** across traits was observed. In the schedule-generation experiments, **500 schedules per condition** were produced. Randomization and the system message weakened positional bias: for example, **Exercise** correlation \(\rho\) dropped from **0.82** under Rand to **0.71** under Sys + Rand, **Reading** from **0.49** to **0.39**, and **Break** from **0.43** to **0.34**. The combination also changed durations and variances for many tasks; **Work** duration moved from **122.84 (32.84)** minutes at baseline to **73.17 (15.93)** under Sys + Rand, while **Coffee** duration moved from **56.07 (10.22)** at baseline to **31.35 (12.65)** under Sys + Rand [2503.19752].

The induced personalities alter both task durations and task frequencies. Reported examples include **Conscientiousness (+)** increasing **Work** duration to **85.1 (19.0)** from **63.9 (19.2)** under Neutral; **Extraversion (+)** increasing **Meeting** duration to **68.0 (16.5)** from **59.0 (17.8)** and **Exercise** duration to **62.5 (13.8)** from **57.1 (17.1)**, while reducing **Coffee** duration to **36.9 (13.9)** from **40.9 (17.3)**; **Agreeableness (−)** increasing **Meeting** duration to **72.0 (20.5)**; and **Openness** conditions frequently increasing **Creative** and **Research** durations. The paper summarizes these outputs qualitatively as pattern-of-life variations: Conscientiousness (+) yields early Plan slots and extended Work blocks, Extraversion (+) shifts Meetings and Collaboration earlier, Agreeableness (−) yields longer and more frequent Meetings, and Openness (+) produces Creative and Research dominance around midday [2503.19752].

A later study moves from planning to **execution-phase decision-making**. Instead of asking the agent merely to generate a schedule, it provides a pre-generated machine-readable schedule in JSON, with each task assigned a duration, an absolute start time, and a **UID computed from a SHA-512 checksum of task name and time**. At each decision cycle the agent receives the persona statement, current time, remaining to-do list, and completed list, and is instructed to **return only the task UID with no additional information**. The completed sequence can then be compared with the original schedule sequence. The study quantifies the transformation using **movement deltas** and normalized sequence metrics: **Longest Common Substring (LCSS)**, **Longest Common Prefix (LCP)**, **Levenshtein Distance (LEV)**, **Longest Common Subsequence and Similarity Ratio (SR)**, and **Hamming Distance (HAM)**. Across **500 schedules per condition**, using **GPT-4o**, **GPT-4o-Mini**, and **GPT-3.5-Turbo**, each trait-condition is compared against a no-persona baseline using independent two-sample Welch’s \(t\)-tests with **Bonferroni correction**, so the adjusted threshold is **\(p \le 0.001\)** [2504.00727].

The execution study reports that **Conscientiousness (Positive)** prioritizes work-oriented tasks such as Work, Email, Planning, Meeting, Research, and Team Collaboration, while **Negative Conscientiousness** moves Coffee Break, Personal Time, and Social Media earlier. **Extraversion (Positive)** prioritizes Team Collaboration, Meeting, Call, and Social Media, whereas **Negative Extraversion** prioritizes Reflective Time, Personal Time, and Reading. The model family matters: **GPT-4o** and **GPT-4o-Mini** reject the null hypothesis for all trait-conditions across measures after Bonferroni correction, while **GPT-3.5-Turbo** rejects it in **41 out of 50 tests** and shows smaller absolute differences. Temperature ablations under a neutral persona show increasing non-determinism with higher temperature. For **GPT-4o**, for example, moving from \(\tau=0.0\) to \(\tau=1.6\) changes **LCSS** from **0.635/0.224** to **0.464/0.223**, **LCP** from **0.604/0.260** to **0.420/0.259**, and **LEV** from **0.201/0.144** to **0.318/0.168**. The paper interprets this as reduced adherence to the original to-do order at higher temperature [2504.00727].

## 6. Interpretive environmental-science usage and the limits of cross-domain unification

A technically distinct, explicitly interpretive usage presents SANDMAN as a framework for predicting realistic surface shear stress and aeolian morphodynamics over complex dune fields by treating the near-surface flow as a mixing layer embedded within the atmospheric surface layer. In that formulation, the ASL is partitioned into a roughness sublayer and an overlying inertial sublayer. Above the mixing-layer thickness \(\delta_\omega\), the mean streamwise velocity follows the log law
\[
u(z)=\frac{u_*}{\kappa}\ln\!\left(\frac{z-d}{z_0}\right),
\]
while within the roughness or mixing layer the report adopts a hyperbolic-tangent profile
\[
\frac{U(z)}{u_{*,d}}=\frac{U_0}{u_{*,d}}\left[1+\tanh\!\left(\frac{z-h_a}{L_s}\right)\right],
\]
with \(h_a = 3 h_{\max}/4\) and \(L_s \approx h_{\max}\) or \(L_s \approx 0.5\delta_\omega\). Surface shear stress follows
\[
\tau_s(x,y)=\rho u_*^2(x,y).
\]
Morphology enters through the stoss–lee partition \(S(x,y)\) and the base proxy
\[
\beta(x,y)=\sqrt{\left(\frac{\partial h}{\partial x}\right)^2+\left(\frac{\partial h}{\partial y}\right)^2}S(x,y),
\]
with model families \(\beta_n=\beta\gamma_n\). Among the proposed models, the mixing-layer family \(\beta_5\)–\(\beta_7\) performed best, and the report states that **\(\beta_5\)** showed the best performance overall. The domain-averaged absolute residuals were reported as **\(\beta_0: 0.20\)**, **\(\beta_1: 0.15\)**, **\(\beta_2: 0.15\)**, **\(\beta_3: 0.17\)**, **\(\beta_4: 0.29\)**, **\(\beta_5: 0.15\)**, **\(\beta_6: 0.17\)**, and **\(\beta_7: 0.15\)** [2004.05136].

The residual analysis attributes the largest localized errors in narrow interdunes to two structural processes: **sediment scour**, arising from spanwise-rotating secondary flows within the mixing layer, and **flow channeling**, arising because flow accelerates within narrow interdunes under geometric obstruction by downwind dunes. The report states that leeward faces generally have low normalized stress, **less than 0.1**, while stoss faces show high-stress bands with **\(\tau_w > 0.4\)** in LES-normalized units, plus localized high-stress pockets in some leeward and interdune areas due to channeling. This usage is explicitly interpretive rather than standardized across the literature, which suggests that not every appearance of SANDMAN denotes a fixed acronym or a unified cross-domain methodology [2004.05136].

Taken together, these usages show that **SANDMAN** functions as a shared label for several unrelated technical objects: a jammer-mitigation receiver algorithm, a personality-conditioned cyber-deception architecture, an execution-time decision-measurement framework for LLM agents, and an interpretive dune-stress modeling approach. The commonality is nominal rather than methodological.

Source: https://www.emergentmind.com/topics/sandman