DecisionDrift: Auditing Temporal Drift in Repeated Decision Systems

Formal framework

1. The decision system as a stochastic process

Let:

\(i = 1, \ldots, N\): units (individuals, cases, applications)
\(t = 1, \ldots, T\): time points (waves, periods, rounds)
\(D_{it} \in \{0, 1\}\): observed binary decision at time \(t\) for unit \(i\)
\(G_i\): group membership (optional)

The decision system is defined as the stochastic process:

\[S = \{ D_{it} : i = 1, \ldots, N;\ t = 1, \ldots, T \}\]

Critically, \(S\) is treated as a generator of decisions over time, not as a parametric model. This makes the framework applicable to hybrid human–AI systems where the decision rule \(f_t\) is only partially observed.

2. The human–AI decision mechanism

In many applied settings, decisions are produced by a joint human–AI process:

\[D_{it} = f_t(X_{it},\ H_{it})\]

where \(X_{it}\) are inputs (features, signals) available to the system, \(H_{it}\) represents human influence (override, discretion, intervention), and \(f_t\) is the time-varying decision mechanism emerging from the interaction of algorithmic and human components.

Drift in this system means \(f_t \neq f_{t'}\), or equivalently:

\[\Pr(D_{it} = 1 \mid X_{it}, H_{it}) \text{ changes over time}\]

DecisionDrift audits changes in \(f_t\) without requiring its full specification. This is the core methodological contribution.

3. Definition of temporal drift

Marginal drift (level shift): a change in the marginal distribution of decisions across waves.

\[\text{Drift exists if } \exists\ t_1 \neq t_2 \text{ such that } P_{t_1} \neq P_{t_2}\]

where \(P_t(d) = \Pr(D_{it} = d)\).

Transition drift (dynamic instability): a change in the conditional distribution given the prior decision.

\[\text{Transition drift exists if } P_t(d_t \mid d_{t-1}) \text{ varies with } t\]

The distinction matters. A system can have stable prevalence but unstable dynamics (transition drift without marginal drift), or shifting prevalence with stable dynamics (marginal drift without transition drift). DecisionDrift separates these two phenomena.

The four drift indices

Decision Drift Index (DDI)

The DDI estimates the linear trend in wave-level decision prevalence:

\[p_t = \frac{1}{N} \sum_{i=1}^{N} D_{it}\]

\[\text{DDI} = \frac{\hat{\beta}}{\text{SD}(p_t)}\]

where \(\hat{\beta}\) is the OLS slope of \(p_t\) on \(t\). Standardising by \(\text{SD}(p_t)\) makes the DDI scale-invariant and comparable across datasets.

Properties:

\(\text{DDI} > 0\): system became more permissive over time
\(\text{DDI} < 0\): system became more restrictive over time
\(\text{DDI} = 0\): no linear trend in decision rate
Independent of \(N\); stable under random reordering of units
Does not capture nonlinearity or abrupt shifts — this motivates the change-point module

Transition Drift Index (TDI)

For the step from wave \(s\) to \(s+1\), define uptake and reversal:

\[u_s = \Pr(D_{i,s+1} = 1 \mid D_{is} = 0), \qquad r_s = \Pr(D_{i,s+1} = 0 \mid D_{is} = 1).\]

Because each row of the transition matrix sums to one, \(u_s\) and \(r_s\) describe it completely. Transition drift between consecutive steps is

\[D^T_s = \tfrac12\left(|u_s - u_{s-1}| + |r_s - r_{s-1}|\right),\]

and the TDI is its mean over the \(T-2\) pairs of consecutive steps:

\[\text{TDI} = \frac{1}{T-2}\sum_{s=2}^{T-1} D^T_s.\]

Properties:

\(\text{TDI} = 0\) when uptake and reversal are constant
Sensitive to policy or model updates that alter switching dynamics
Can be large while prevalence is flat (see Flow decomposition below)
Descriptive: it is never exactly zero in finite samples, so use dd_global_test() for a formal test

Group Differential Drift (GDD)

Let \(\text{DDI}^{(g)}\) denote the DDI estimated within group \(g\). For groups \(A\) and \(B\):

\[\text{GDD}_{AB} = \text{DDI}^{(A)} - \text{DDI}^{(B)}\]

GDD measures inequality in system evolution, not static disparity. A positive \(\text{GDD}_{AB}\) indicates the system became more permissive for group \(A\) faster than for group \(B\). A value near zero indicates parallel drift regardless of any baseline disparity.

Cumulative Drift Burden (CDB)

\[\text{CDB} = \sum_{t=2}^{T} |p_t - p_{t-1}|\]

CDB captures total accumulated volatility in the decision rate, regardless of direction. Unlike the DDI, CDB is non-zero even when drift oscillates (e.g., the system alternates between permissive and restrictive periods). A high CDB with a near-zero DDI indicates instability without a directional trend.

Modules

The five core modules each estimate one aspect of drift:

Module	Stochastic object estimated	Index
`dd_prevalence()`	\(\Pr(D_t = 1)\) over time	DDI
`dd_transition()`	\(\Pr(D_t \mid D_{t-1})\) over time	TDI
`dd_entropy_trend()`	Complexity of path distribution	—
`dd_group_drift()`	Heterogeneity in \(\Pr(D_t)\) across \(G\)	GDD
`dd_changepoint()`	Structural break in process	—
`dd_decompose()`	Inflow and outflow behind each change in \(\Pr(D_t = 1)\)	NEC, CMB, CTB
`dd_group_decompose()`	Within-group vs. composition change	\(D^C\)
`dd_global_test()`	Constancy of uptake, reversal, prevalence	bootstrap test

Together they answer: Did the system change, and how? The robustness and sensitivity modules then ask: Is that conclusion credible? dd_simulate() generates panels with known drift for checking methods.

Worked example

# Simulate a system that became more permissive after wave 4.
# Group A drifts faster than Group B.

n_units <- 80
n_waves <- 8

probs_A <- c(rep(0.20, 4), rep(0.60, 4))  # sharp increase at wave 5
probs_B <- c(rep(0.25, 4), rep(0.40, 4))  # modest increase at wave 5

dat <- data.frame(
  id       = rep(seq_len(n_units), each = n_waves),
  time     = rep(seq_len(n_waves), times = n_units),
  decision = c(
    rbinom(40 * n_waves, 1, rep(probs_A, 40)),
    rbinom(40 * n_waves, 1, rep(probs_B, 40))
  ),
  group    = rep(c("A", "B"), each = 40 * n_waves)
)

dp <- dd_build(dat, id, time, decision,
               group      = group,
               event_time = 5L)
print(dp)
#> 
#> ── DecisionDrift Panel Object ──────────────────────────────────────────────────
#> • Units: 80
#> • Waves: 8 (1–8)
#> • Balanced: TRUE
#> • Group var: group
#> • Event time: 5
#> • Units dropped (min_waves): 0

Module 1 — Prevalence drift

prev <- dd_prevalence(dp)
print(prev)
#> 
#> ── Prevalence Drift (Module 1) ─────────────────────────────────────────────────
#> • Mean decision rate: 0.359
#> • Trend slope: 0.0557 (p = 0.0191)
#> • R²: 0.627
#> • Cumulative change: 0.4
#> • DDI: 0.323
plot(prev)

The DDI is positive and the slope is statistically significant, confirming that the overall decision rate increased over time.

Module 2 — Transition drift

tr <- dd_transition(dp)
print(tr)
#> 
#> ── Transition Drift (Module 2) ─────────────────────────────────────────────────
#> • TDI (Transition Drift Index): 0.1416
#> • Uptake drift mean |Delta P(1|0)|: 0.1513
#> • Reversal drift mean |Delta P(0|1)|: 0.1319
#> 
#> ── Linear trends in transition probabilities ──
#> 
#>   p11: slope = 0.0566, p = 0.1089
#>   p10: slope = -0.0566, p = 0.1089
#>   p01: slope = 0.0465, p = 0.1163
#>   p00: slope = -0.0465, p = 0.1163
plot(tr)

The TDI captures the instability in switching and persistence dynamics that accompanies the structural break at wave 5.

Module 3 — Entropy and stability trend

et <- dd_entropy_trend(dp, window = 3L)
print(et)
#> 
#> ── Entropy & Stability Trend (Module 3) ────────────────────────────────────────
#> • Method: binary
#> • Window: 3 waves
#> • Entropy trend slope: 0.0618 (p = 0.0107)
#> • Switching trend slope: 0.0296 (p = 0.0402)
plot(et)

Module 4 — Group-differential drift

gd <- dd_group_drift(dp)
print(gd)
#> 
#> ── Group-Differential Drift (Module 4) ─────────────────────────────────────────
#> 
#> ── Per-group trend slopes ──
#> 
#> # A tibble: 2 × 5
#>   group  slope     se p_value r_squared
#>   <chr>  <dbl>  <dbl>   <dbl>     <dbl>
#> 1 A     0.0729 0.0282  0.0412     0.528
#> 2 B     0.0384 0.0135  0.0297     0.573
#> ── GDD table ──
#> # A tibble: 1 × 4
#>   group_a group_b    GDD direction
#>   <chr>   <chr>    <dbl> <chr>    
#> 1 A       B       0.0345 A faster
#> • Gap trajectory: diverging (slope = 0.0345, p = 0.2468)
plot(gd)

Group A experienced faster drift than Group B (positive GDD). The gap trajectory shows divergence over time.

Module 5 — Change-point detection

cp <- dd_changepoint(dp)
print(cp)
#> 
#> ── Change-Point & Regime Detection (Module 5) ──────────────────────────────────
#> 
#> ── CUSUM ──
#> 
#> • Detected break wave: 4
#> • Max |CUSUM|: -3.631
#> 
#> ── Segmented regression ──
#> 
#> • Best breakpoint: 6
#> • delta_AIC (null - seg): 1.58
#> 
#> ── Event alignment ──
#> 
#> • Event wave: 5
#> • Pre-mean: 0.203
#> • Post-mean: 0.516
#> • Change: 0.312
#> • p-value: 5e-04
#> • p < 0.05: TRUE
plot(cp)

Both the CUSUM and segmented regression methods identify a structural break near wave 5, consistent with the known event time.

All four indices in one call

idx <- dd_indices(dp)
print(idx)
#> 
#> ── DecisionDrift Summary Indices ───────────────────────────────────────────────
#> • DDI (Decision Drift Index): 0.3233
#> • TDI (Transition Drift Index): 0.1416
#> • GDD (Group Differential Drift): 0.0345
#> • CDB (Cumulative Drift Burden): 0.6125

Full audit

The audit runs every module, one shared cluster bootstrap, and the global stability test. It does not attach labels such as “strong drift”. Its conclusion states the test result, and any practical cut-offs are supplied by the user through thresholds.

aud <- dd_audit(dp, include_robustness = TRUE, R = 199, seed = 1,
                thresholds = c(TDI = 0.05, NEC = 0.10), verbose = FALSE)
print(aud)
#> 
#> ── DecisionDrift Audit Report ──────────────────────────────────────────────────
#> • Units: 80 | Waves: 8 | Balanced: TRUE
#> • Group var: group
#> • Event time: 5
#> 
#> ── Summary Indices ──
#> 
#> ── DecisionDrift Summary Indices ───────────────────────────────────────────────
#> • DDI (Decision Drift Index): 0.3233
#> • TDI (Transition Drift Index): 0.1416
#> • GDD (Group Differential Drift): 0.0345
#> • CDB (Cumulative Drift Burden): 0.6125
#> 
#> ── Prevalence Drift ──
#> 
#> • DDI = 0.323 | slope = 0.0557 | p = 0.0191
#> 
#> ── Transition Drift ──
#> 
#> • TDI = 0.1416 | uptake drift = 0.1513 | reversal drift = 0.1319
#> 
#> ── Flow Decomposition ──
#> 
#> • NEC = 0.2625 [0.125, 0.363]
#> • CMB = 0.6125 [0.499, 1.100]
#> • turnover_total = 2.8375 [2.524, 3.089]
#> • CTB = 0.8495 [0.741, 1.408]
#> 
#> ── Change-point Detection ──
#> 
#> • CUSUM break: wave 4
#> • Segmented break: wave 6 (delta_AIC = 1.58)
#> 
#> ── Group-Differential Drift ──
#> 
#> # A tibble: 1 × 4
#>   group_a group_b    GDD direction
#>   <chr>   <chr>    <dbl> <chr>    
#> 1 A       B       0.0345 A faster
#> • Within-group change (total): 0.2625
#> • Composition change (total): 0.0000
#> 
#> ── Global Stability Test ──
#> 
#> • max statistic = 5.044, bootstrap p = 0.005 (R = 199)
#> • Contrasts whose simultaneous band excludes 0: 1 of 12
#> 
#> ── User Thresholds ──
#> 
#> • TDI: |0.1416| >= 0.05
#> • NEC: |0.2625| >= 0.1
#> 
#> ── Robustness ──
#> 
#> • Fragility index: 0
#> ────────────────────────────────────────────────────────────────────────────────
#> ℹ Stability of uptake and reversal rejected at alpha = 0.05 (bootstrap p = 0.005).
#> ────────────────────────────────────────────────────────────────────────────────

Flow decomposition and masking

Prevalence can stay flat while the process underneath changes. The marginal-transition identity makes this exact:

\[\pi_{s+1} - \pi_s = \underbrace{(1-\pi_s)\,u_s}_{\text{inflow}} - \underbrace{\pi_s\,r_s}_{\text{outflow}}.\]

If inflow and outflow rise together, prevalence does not move. The "masked" scenario in dd_simulate() does exactly this: uptake and reversal both rise from 0.08 to 0.32 over five steps while the positive rate stays near 0.5.

masked <- dd_simulate(n = 600, waves = 6, scenario = "masked", seed = 11)
dpm <- dd_build(masked, id, time, decision)
round(tapply(masked$decision, masked$time, mean), 3)
#>     1     2     3     4     5     6 
#> 0.483 0.493 0.492 0.485 0.503 0.520

fl <- dd_decompose(dpm, R = 199, seed = 2)
print(fl)
#> 
#> ── Flow Decomposition: change = inflow - outflow ───────────────────────────────
#>  step   n uptake reversal inflow outflow    net turnover
#>  1->2 600  0.097    0.083  0.050   0.040  0.010    0.090
#>  2->3 600  0.128    0.135  0.065   0.067 -0.002    0.132
#>  3->4 600  0.174    0.193  0.088   0.095 -0.007    0.183
#>  4->5 600  0.227    0.203  0.117   0.098  0.018    0.215
#>  5->6 600  0.332    0.295  0.165   0.148  0.017    0.313
#> 
#> ── Summary ──
#> 
#> • NEC: 0.0367 [0.0017, 0.0783]
#> • CMB: 0.0533 [0.0349, 0.1334]
#> • CTB: 0.2237 [0.1892, 0.3010]
#> • TDI: 0.0559 [0.0473, 0.0753]
#> • turnover_total: 0.9333 [0.8716, 1.0221]
#> • net_flow_total: 0.0533 [0.0349, 0.1334]
#> 95% cluster-bootstrap percentile intervals, R = 199.
plot(fl)

Net change (net) stays near zero at every step while turnover more than triples. In the summary, net endpoint change (NEC) and cumulative marginal burden (CMB) are small, but total turnover and cumulative transition burden (CTB) are large. Intervals come from a unit-level cluster bootstrap, which keeps each unit’s full history together. Intervals for quantities defined as absolute values (NEC, CMB, CTB, TDI) cannot include zero and are biased upward when the true value is near zero; use the global test, not these intervals, to decide whether the process changed.

Global stability test

dd_global_test() tests whether uptake and reversal were constant over all steps. It uses the same centred cluster bootstrap and reports familywise-adjusted p-values and simultaneous bands for each consecutive change, so it also shows where the process changed.

gt <- dd_global_test(dpm, R = 199, seed = 3)
print(gt)
#> 
#> ── Global Test of Decision Process Stability ───────────────────────────────────
#> • H0: uptake, reversal constant across waves
#> • Statistic: max = 3.358 (consecutive contrasts)
#> • Bootstrap p-value: 0.01 (R = 199)
#> • Contrasts tested: 8
#> 
#> ── Contrasts (familywise-adjusted) ──
#> 
#>  component group         contrast estimate   lower  upper p_adj
#>     uptake       (5->6) vs (4->5)   0.1057  0.0215 0.1899 0.010
#>   reversal       (5->6) vs (4->5)   0.0920  0.0007 0.1832 0.045
#>   reversal       (2->3) vs (1->2)   0.0524 -0.0224 0.1271 0.330
#>   reversal       (3->4) vs (2->3)   0.0581 -0.0249 0.1410 0.330
#>     uptake       (4->5) vs (3->4)   0.0528 -0.0343 0.1398 0.460
#>     uptake       (3->4) vs (2->3)   0.0455 -0.0363 0.1273 0.595
#>     uptake       (2->3) vs (1->2)   0.0315 -0.0364 0.0994 0.775
#>   reversal       (4->5) vs (3->4)   0.0095 -0.0799 0.0989 1.000
#> Bands are 95% simultaneous (max-t critical value 2.68).
plot(gt)

Compare the prevalence trend test from dd_prevalence():

dd_prevalence(dpm)$trend$p_value
#> [1] 0.05230862

Expected prevalence is constant in this scenario, so a prevalence test has nothing to find; the transition test targets the change that did happen. A rejection says the decision-generating process was not constant. It does not say why, and it is not a causal effect.

By default each step is compared with the one before it, which localises abrupt change. For gradual drift, contrast = "baseline" compares each step with the first one; small step-to-step changes then add up, so this version has more power against steady trends.

dd_global_test(dpm, contrast = "baseline", R = 199, seed = 3)$p_value
#> [1] 0.005

Within-group and composition change

The overall rate is a weighted average of group rates, \(\pi_t = \sum_g w_{gt}\pi_{gt}\). A change in \(\pi_t\) can come from the group rates (within-group change) or from the group shares (composition change). dd_group_decompose() uses a symmetric midpoint decomposition,

\[\Delta\pi_t = \sum_g \bar w_{gt}\,\Delta\pi_{gt} + \sum_g \bar\pi_{gt}\,\Delta w_{gt},\]

which is exact and does not depend on which wave is the baseline.

In the "composition" scenario, both groups follow stable processes, but the higher-rate group A enters the panel over time, so its share grows.

comp <- dd_simulate(n = 600, waves = 6, scenario = "composition", seed = 12)
dpc  <- dd_build(comp, id, time, decision, group = group)
gdc  <- dd_group_decompose(dpc, R = 199, seed = 4)
print(gdc)
#> 
#> ── Within-Group and Composition Decomposition ──────────────────────────────────
#>  step delta_pi  within composition    D_C
#>  1->2   0.0702  0.0165      0.0537 0.1365
#>  2->3   0.0296 -0.0084      0.0380 0.0988
#>  3->4  -0.0267 -0.0267      0.0000 0.0000
#>  4->5   0.0133  0.0133      0.0000 0.0000
#>  5->6   0.0183  0.0183      0.0000 0.0000
#> 
#> ── Totals ──
#> 
#> • within_total: 0.0131 [-0.0354, 0.0661]
#> • composition_total: 0.0917 [0.0748, 0.1108]
#> 
#> ── Group-specific uptake and reversal (mean over steps) ──
#> 
#> • A: uptake = 0.323, reversal = 0.140
#> • B: uptake = 0.160, reversal = 0.341
plot(gdc)

Almost all of the rise in the overall rate is composition change. A prevalence-only audit would attribute it to a change in the decision rule.

The reverse also happens: group rates can move in opposite directions while the overall rate stays flat. Testing group-specific parameters with by_group = TRUE checks for that. Because the divergence is gradual, baseline contrasts are used.

gm  <- dd_simulate(n = 800, waves = 6, scenario = "group_masked", seed = 13)
dpg <- dd_build(gm, id, time, decision, group = group)
round(tapply(gm$decision, gm$time, mean), 3)   # pooled rate
#>     1     2     3     4     5     6 
#> 0.489 0.496 0.494 0.505 0.478 0.479
gtg <- dd_global_test(dpg, components = "prevalence", by_group = TRUE,
                      contrast = "baseline", R = 199, seed = 5)
print(gtg)
#> 
#> ── Global Test of Decision Process Stability ───────────────────────────────────
#> • H0: prevalence constant across waves (within each group)
#> • Statistic: max = 3.072 (baseline contrasts)
#> • Bootstrap p-value: 0.03 (R = 199)
#> • Contrasts tested: 10
#> 
#> ── Contrasts (familywise-adjusted) ──
#> 
#>   component group contrast estimate   lower   upper p_adj
#>  prevalence     B   6 vs 1  -0.1025 -0.2002 -0.0048 0.030
#>  prevalence     A   6 vs 1   0.0825 -0.0150  0.1800 0.110
#>  prevalence     B   5 vs 1  -0.0750 -0.1704  0.0204 0.140
#>  prevalence     A   4 vs 1   0.0700 -0.0248  0.1648 0.185
#>  prevalence     A   5 vs 1   0.0525 -0.0463  0.1513 0.550
#>  prevalence     B   4 vs 1  -0.0375 -0.1181  0.0431 0.700
#>  prevalence     A   2 vs 1   0.0050 -0.0579  0.0679 1.000
#>  prevalence     A   3 vs 1   0.0125 -0.0738  0.0988 1.000
#>  prevalence     B   2 vs 1   0.0100 -0.0543  0.0743 1.000
#>  prevalence     B   3 vs 1  -0.0025 -0.0822  0.0772 1.000
#> Bands are 95% simultaneous (max-t critical value 2.93).

Simulation scenarios

dd_simulate() provides stable, marginal, masked, abrupt, group-masked, and composition-change panels, plus custom uptake and reversal sequences. The script in system.file("simulation", "mc_study.R", package = "DecisionDrift") runs a Monte Carlo study comparing the prevalence trend test with the global stability test across the first four scenarios.

Robustness and sensitivity

A key claim of the DecisionDrift framework is that observed drift is not an artefact of analytic choices or data problems. The robustness and sensitivity modules test this claim directly.

Robustness (dd_robustness()) tests whether the DDI sign and magnitude are stable across:

Balanced vs. unbalanced panels
Leave-one-period-out (LOPO)
Leave-one-group-out (LOGO)
Alternative minimum follow-up requirements

A fragility index summarises the proportion of analytic variants in which the slope changes sign. Values near zero indicate robust conclusions.

Sensitivity (dd_sensitivity()) probes vulnerability to plausible data problems:

Decision miscoding
Missing-wave attrition
Threshold shifts (when decisions derive from scores)
Subgroup composition shifts

A tipping-point estimate identifies the smallest perturbation level at which more than 50 per cent of resampled conclusions flip sign.

rob <- dd_robustness(dp, variants = c("lopo", "min_waves"))
print(rob)
#> 
#> ── Robustness Analysis (Module 6) ──────────────────────────────────────────────
#> • Baseline DDI: 0.323
#> • Fragility index: 0
#> 
#> Robustness table:
#> # A tibble: 12 × 6
#>    variant            DDI  slope p_value n_waves n_units
#>  * <chr>            <dbl>  <dbl>   <dbl>   <int>   <int>
#>  1 Baseline         0.323 0.0557  0.0191       8      80
#>  2 Leave out wave 1 0.341 0.0571  0.0591       7      80
#>  3 Leave out wave 2 0.313 0.0540  0.0499       7      80
#>  4 Leave out wave 3 0.303 0.0540  0.0399       7      80
#>  5 Leave out wave 4 0.312 0.0539  0.0228       7      80
#>  6 Leave out wave 5 0.331 0.0531  0.0103       7      80
#>  7 Leave out wave 6 0.305 0.0515  0.0376       7      80
#>  8 Leave out wave 7 0.314 0.0545  0.0487       7      80
#>  9 Leave out wave 8 0.396 0.0723  0.0143       7      80
#> 10 Min waves >= 2   0.323 0.0557  0.0191       8      80
#> 11 Min waves >= 3   0.323 0.0557  0.0191       8      80
#> 12 Min waves >= 4   0.323 0.0557  0.0191       8      80
plot(rob)

DecisionDrift: Auditing Temporal Drift in Repeated Decision Systems

Subir Hait

2026-10-16

Overview

Formal framework

1. The decision system as a stochastic process

2. The human–AI decision mechanism

3. Definition of temporal drift

The four drift indices

Decision Drift Index (DDI)

Transition Drift Index (TDI)

Group Differential Drift (GDD)

Cumulative Drift Burden (CDB)

Modules

Worked example

Module 1 — Prevalence drift

Module 2 — Transition drift

Module 3 — Entropy and stability trend

Module 4 — Group-differential drift

Module 5 — Change-point detection

All four indices in one call

Full audit

Flow decomposition and masking

Global stability test

Within-group and composition change

Simulation scenarios

Robustness and sensitivity

Conceptual positioning

Relationship to `decisionpaths`

References

DecisionDrift: Auditing Temporal Drift in Repeated Decision Systems

Subir Hait

2026-10-16

Overview

Formal framework

1. The decision system as a stochastic process

2. The human–AI decision mechanism

3. Definition of temporal drift

The four drift indices

Decision Drift Index (DDI)

Transition Drift Index (TDI)

Group Differential Drift (GDD)

Cumulative Drift Burden (CDB)

Modules

Worked example

Module 1 — Prevalence drift

Module 2 — Transition drift

Module 3 — Entropy and stability trend

Module 4 — Group-differential drift

Module 5 — Change-point detection

All four indices in one call

Full audit

Flow decomposition and masking

Global stability test

Within-group and composition change

Simulation scenarios

Robustness and sensitivity

Conceptual positioning

Relationship to decisionpaths

References

Relationship to `decisionpaths`