diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index ffe514db6..78c33da18 100644
--- a/ARCHITECTURE.md
+++ b/ARCHITECTURE.md
@@ -61,6 +61,7 @@ boundaries above remain the target modular MSA architecture.
 | `tepp_simulation` | known-truth temporal/event data generation |
 | `validation_core` | RMSE, bias, coverage, graph, and Monte Carlo metrics |
 | `tepp_api` | versioned DTO, schema, and export contracts |
+| `measurement_invariance` | configural/metric/scalar status; loading RMSE; no shared meaning from configural only |
 
 No crate exposes placeholder production behavior in Task 1. This prevents an
 empty façade from becoming a de facto public API before its invariants and tests
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0f83a9137..078c70ff0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,7 @@ All notable changes to TEPP are documented here. The format follows Keep a Chang
 
 ### Added
 
+- `measurement_invariance` explicit invariance status: configural structure cannot license shared metric meaning; metric and scalar status may; recovered group loadings match known truth with lower computed RMSE than a crossed-language collapse.
 - `persistence_postgres` concurrent document-write stress: atomic revise `DO` block that requires exactly one open `system_to` close, SQLSTATE mapping onto `ConcurrentWriteConflict` / `DuplicateDocumentRecord`, and live multi-session insert/revise/append-only proofs. No new migration number.
 - `tepp_api` naruon HTTP interchange: versioned `https` POST contracts for analysis-run create and modular export authorization that refuse table-access URLs, review/Copilot credential headers, reserved standard-header redefinition, principal-only export idempotency keys, and lexical inference claims (ADR 0011).
 - `persistence_postgres` audit-event SQL contracts: append-only insert that refuses empty, oversized, or hostile `action_code` values before SQL is rendered.
diff --git a/Cargo.lock b/Cargo.lock
index 372a55f43..57d90d815 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -697,6 +697,10 @@ dependencies = [
  "digest",
 ]
 
+[[package]]
+name = "measurement_invariance"
+version = "0.1.0"
+
 [[package]]
 name = "membership_core"
 version = "0.1.0"
diff --git a/Cargo.toml b/Cargo.toml
index 925659406..937649522 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -11,6 +11,7 @@ members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/measurement_invariance",
 ]
 default-members = [
     "crates/evidence_core",
@@ -23,6 +24,7 @@ default-members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/measurement_invariance",
 ]
 
 [workspace.package]
diff --git a/README.md b/README.md
index ae74015d3..9c1a9c461 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@ implemented in Rust.
 ## Current implementation state
 
 This branch establishes the Task 1 Rust workspace and quality-gate foundation.
-The ten bounded crates compile independently but intentionally expose no
+The eleven bounded crates compile independently but intentionally expose no
 placeholder production APIs. Domain behavior begins in Task 2 with immutable
 evidence identifiers and source records.
 
@@ -22,6 +22,7 @@ crates/corpus_split
 crates/tepp_simulation
 crates/validation_core
 crates/tepp_api
+crates/measurement_invariance
 ```
 
 ## Local verification
diff --git a/crates/measurement_invariance/Cargo.toml b/crates/measurement_invariance/Cargo.toml
new file mode 100644
index 000000000..95c6e157a
--- /dev/null
+++ b/crates/measurement_invariance/Cargo.toml
@@ -0,0 +1,17 @@
+[package]
+name = "measurement_invariance"
+description = "Explicit invariance status gates and group-loading RMSE."
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+repository.workspace = true
+homepage.workspace = true
+readme.workspace = true
+keywords.workspace = true
+categories.workspace = true
+publish = false
+
+[lints]
+workspace = true
diff --git a/crates/measurement_invariance/src/error.rs b/crates/measurement_invariance/src/error.rs
new file mode 100644
index 000000000..4fa37f538
--- /dev/null
+++ b/crates/measurement_invariance/src/error.rs
@@ -0,0 +1,53 @@
+//! Fail-closed measurement-invariance errors.
+
+use std::fmt;
+
+/// A fail-closed measurement-invariance error.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+#[non_exhaustive]
+pub enum InvarianceError {
+    /// A weaker invariance status was treated as shared metric meaning.
+    InvarianceTooWeakForSharedMeaning,
+    /// An unknown invariance-status wire name was supplied.
+    UnknownInvarianceLevel,
+    /// Loading slices were empty, length-mismatched, or non-finite.
+    InvalidLoadingPayload,
+}
+
+impl fmt::Display for InvarianceError {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let message = match self {
+            Self::InvarianceTooWeakForSharedMeaning => "invariance is too weak for shared meaning",
+            Self::UnknownInvarianceLevel => "unknown invariance level",
+            Self::InvalidLoadingPayload => "invalid invariance loading payload",
+        };
+        formatter.write_str(message)
+    }
+}
+
+impl std::error::Error for InvarianceError {}
+
+#[cfg(test)]
+mod tests {
+    use super::InvarianceError;
+
+    #[test]
+    fn error_messages_are_stable() {
+        for (error, message) in [
+            (
+                InvarianceError::InvarianceTooWeakForSharedMeaning,
+                "invariance is too weak for shared meaning",
+            ),
+            (
+                InvarianceError::UnknownInvarianceLevel,
+                "unknown invariance level",
+            ),
+            (
+                InvarianceError::InvalidLoadingPayload,
+                "invalid invariance loading payload",
+            ),
+        ] {
+            assert_eq!(error.to_string(), message);
+        }
+    }
+}
diff --git a/crates/measurement_invariance/src/lib.rs b/crates/measurement_invariance/src/lib.rs
new file mode 100644
index 000000000..b578be7f0
--- /dev/null
+++ b/crates/measurement_invariance/src/lib.rs
@@ -0,0 +1,23 @@
+#![forbid(unsafe_code)]
+#![deny(missing_docs)]
+#![allow(clippy::cast_precision_loss)]
+//! Explicit invariance status and group-loading recovery for shared meaning.
+//!
+//! Configural structure alone cannot license shared metric meaning. Metric and
+//! scalar status may; recovery reports computed loading RMSE against known
+//! truth (ADR 0004/0005).
+
+mod error;
+mod loading;
+mod status;
+
+/// Fail-closed measurement-invariance errors.
+pub use error::InvarianceError;
+/// One group-specific loading.
+pub use loading::GroupLoading;
+/// RMSE of recovered loadings against known truth.
+pub use loading::loading_root_mean_square_error;
+/// Established invariance status.
+pub use status::InvarianceLevel;
+/// Refuse to treat a weaker status as shared meaning.
+pub use status::refuse_noninvariant_as_shared_meaning;
diff --git a/crates/measurement_invariance/src/loading.rs b/crates/measurement_invariance/src/loading.rs
new file mode 100644
index 000000000..57142f4db
--- /dev/null
+++ b/crates/measurement_invariance/src/loading.rs
@@ -0,0 +1,87 @@
+//! Known-truth RMSE for multi-group loadings.
+
+use crate::InvarianceError;
+
+/// One group-specific loading used for invariance recovery.
+#[derive(Clone, Copy, Debug, PartialEq)]
+pub struct GroupLoading {
+    group_index: u32,
+    loading: f64,
+}
+
+impl GroupLoading {
+    /// Construct a finite group loading.
+    ///
+    /// Non-finite values are rejected later by
+    /// [`loading_root_mean_square_error`]; this constructor keeps the record
+    /// transparent so tests can compute the same residual.
+    #[must_use]
+    pub const fn new(group_index: u32, loading: f64) -> Self {
+        Self {
+            group_index,
+            loading,
+        }
+    }
+
+    /// Return the group index.
+    #[must_use]
+    pub const fn group_index(self) -> u32 {
+        self.group_index
+    }
+
+    /// Return the loading value.
+    #[must_use]
+    pub const fn loading(self) -> f64 {
+        self.loading
+    }
+}
+
+/// RMSE of recovered loadings against known-truth loadings.
+///
+/// # Errors
+///
+/// Returns [`InvarianceError::InvalidLoadingPayload`] when either slice is
+/// empty, the lengths differ, a group index mismatches, or a loading is
+/// non-finite.
+pub fn loading_root_mean_square_error(
+    truth: &[GroupLoading],
+    decided: &[GroupLoading],
+) -> Result<f64, InvarianceError> {
+    if truth.is_empty() || truth.len() != decided.len() {
+        return Err(InvarianceError::InvalidLoadingPayload);
+    }
+    let mut sum_squares = 0.0_f64;
+    for (truth_row, decided_row) in truth.iter().zip(decided) {
+        if truth_row.group_index() != decided_row.group_index()
+            || !truth_row.loading().is_finite()
+            || !decided_row.loading().is_finite()
+        {
+            return Err(InvarianceError::InvalidLoadingPayload);
+        }
+        let residual = decided_row.loading() - truth_row.loading();
+        sum_squares += residual * residual;
+    }
+    Ok((sum_squares / truth.len() as f64).sqrt())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{GroupLoading, loading_root_mean_square_error};
+    use crate::InvarianceError;
+
+    #[test]
+    fn mismatched_groups_and_nan_fail_closed() {
+        let truth = [GroupLoading::new(0, 0.5)];
+        let other_group = [GroupLoading::new(1, 0.5)];
+        assert_eq!(
+            loading_root_mean_square_error(&truth, &other_group),
+            Err(InvarianceError::InvalidLoadingPayload)
+        );
+        let nan = [GroupLoading::new(0, f64::NAN)];
+        assert_eq!(
+            loading_root_mean_square_error(&truth, &nan),
+            Err(InvarianceError::InvalidLoadingPayload)
+        );
+        assert_eq!(GroupLoading::new(2, 0.1).group_index(), 2);
+    }
+}
diff --git a/crates/measurement_invariance/src/status.rs b/crates/measurement_invariance/src/status.rs
new file mode 100644
index 000000000..e0e577dd2
--- /dev/null
+++ b/crates/measurement_invariance/src/status.rs
@@ -0,0 +1,86 @@
+//! Explicit invariance status that may or may not license shared meaning.
+
+use crate::InvarianceError;
+
+/// Established invariance status for a multi-group comparison.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+pub enum InvarianceLevel {
+    /// Same factor structure only; loadings are not comparable.
+    Configural,
+    /// Equal loadings; factor variances/means remain group-specific.
+    Metric,
+    /// Equal loadings and intercepts.
+    Scalar,
+}
+
+impl InvarianceLevel {
+    /// Stable wire name.
+    #[must_use]
+    pub const fn wire_name(self) -> &'static str {
+        match self {
+            Self::Configural => "configural",
+            Self::Metric => "metric",
+            Self::Scalar => "scalar",
+        }
+    }
+
+    /// Parse a stable wire invariance-status name.
+    ///
+    /// # Errors
+    ///
+    /// Returns [`InvarianceError::UnknownInvarianceLevel`] for unrecognized names.
+    pub fn from_wire_name(name: &str) -> Result<Self, InvarianceError> {
+        match name {
+            "configural" => Ok(Self::Configural),
+            "metric" => Ok(Self::Metric),
+            "scalar" => Ok(Self::Scalar),
+            _ => Err(InvarianceError::UnknownInvarianceLevel),
+        }
+    }
+
+    /// Return whether this status licenses shared metric meaning.
+    #[must_use]
+    pub const fn licenses_shared_meaning(self) -> bool {
+        matches!(self, Self::Metric | Self::Scalar)
+    }
+}
+
+/// Refuse to treat a weaker invariance status as shared meaning.
+///
+/// # Errors
+///
+/// Returns [`InvarianceError::InvarianceTooWeakForSharedMeaning`] when the
+/// status is only configural.
+pub fn refuse_noninvariant_as_shared_meaning(
+    level: InvarianceLevel,
+) -> Result<(), InvarianceError> {
+    if level.licenses_shared_meaning() {
+        Ok(())
+    } else {
+        Err(InvarianceError::InvarianceTooWeakForSharedMeaning)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::InvarianceLevel;
+    use crate::InvarianceError;
+
+    #[test]
+    fn wire_names_round_trip() {
+        for level in [
+            InvarianceLevel::Configural,
+            InvarianceLevel::Metric,
+            InvarianceLevel::Scalar,
+        ] {
+            assert_eq!(
+                InvarianceLevel::from_wire_name(level.wire_name()).expect("round trip"),
+                level
+            );
+        }
+        assert_eq!(
+            InvarianceLevel::from_wire_name("partial"),
+            Err(InvarianceError::UnknownInvarianceLevel)
+        );
+    }
+}
diff --git a/crates/measurement_invariance/tests/crate_contract.rs b/crates/measurement_invariance/tests/crate_contract.rs
new file mode 100644
index 000000000..65abcc7eb
--- /dev/null
+++ b/crates/measurement_invariance/tests/crate_contract.rs
@@ -0,0 +1,7 @@
+//! Integration contract for the `measurement_invariance` package identity.
+
+#[test]
+fn package_identity_is_stable() {
+    let observed = std::hint::black_box(env!("CARGO_PKG_NAME"));
+    assert_eq!(observed, "measurement_invariance");
+}
diff --git a/crates/measurement_invariance/tests/invariance_status_contract.rs b/crates/measurement_invariance/tests/invariance_status_contract.rs
new file mode 100644
index 000000000..1615173e5
--- /dev/null
+++ b/crates/measurement_invariance/tests/invariance_status_contract.rs
@@ -0,0 +1,60 @@
+//! Shared meaning requires an explicit invariance status and computed loading RMSE.
+
+use measurement_invariance::{
+    GroupLoading, InvarianceError, InvarianceLevel, loading_root_mean_square_error,
+    refuse_noninvariant_as_shared_meaning,
+};
+
+#[test]
+fn configural_status_cannot_claim_shared_metric_meaning() {
+    assert_eq!(
+        refuse_noninvariant_as_shared_meaning(InvarianceLevel::Configural),
+        Err(InvarianceError::InvarianceTooWeakForSharedMeaning)
+    );
+    assert_eq!(
+        refuse_noninvariant_as_shared_meaning(InvarianceLevel::Metric),
+        Ok(())
+    );
+    assert_eq!(
+        refuse_noninvariant_as_shared_meaning(InvarianceLevel::Scalar),
+        Ok(())
+    );
+}
+
+#[test]
+fn aligned_loadings_have_lower_computed_rmse_than_a_crossed_collapse() {
+    let truth = [
+        GroupLoading::new(0, 0.80),
+        GroupLoading::new(1, 0.80),
+        GroupLoading::new(0, 0.40),
+        GroupLoading::new(1, 0.40),
+    ];
+    let aligned = truth;
+    let crossed = [
+        GroupLoading::new(0, 0.80),
+        GroupLoading::new(1, 0.40),
+        GroupLoading::new(0, 0.40),
+        GroupLoading::new(1, 0.80),
+    ];
+
+    let aligned_rmse = loading_root_mean_square_error(&truth, &aligned).expect("aligned");
+    let crossed_rmse = loading_root_mean_square_error(&truth, &crossed).expect("crossed");
+    let expected = {
+        let mut sum_squares = 0.0_f64;
+        for (truth_row, decided_row) in truth.iter().zip(aligned.iter()) {
+            let residual = decided_row.loading() - truth_row.loading();
+            sum_squares += residual * residual;
+        }
+        (sum_squares / f64::from(u32::try_from(truth.len()).expect("len"))).sqrt()
+    };
+    assert!((aligned_rmse - expected).abs() < f64::EPSILON);
+    assert!(aligned_rmse < crossed_rmse);
+}
+
+#[test]
+fn empty_or_non_finite_loadings_fail_closed() {
+    assert_eq!(
+        loading_root_mean_square_error(&[], &[]),
+        Err(InvarianceError::InvalidLoadingPayload)
+    );
+}
diff --git a/docs/TRACEABILITY.md b/docs/TRACEABILITY.md
index afada87ae..ac98e0672 100644
--- a/docs/TRACEABILITY.md
+++ b/docs/TRACEABILITY.md
@@ -21,7 +21,7 @@ The full APA 7th standards/literature register remains `docs/research/standards-
 | known-truth temporal/event simulation manifests | PRD; TRD; Test Strategy | `tepp_simulation` on protected main; recovery metrics in `validation_core` | implemented-main |
 | versioned service/API contracts and exports | PRD; API contract; ADR 0011/0013 | `tepp_api` analysis-run/export/JSON-LD/GraphML contracts on protected main (PR #21); HTTP service remaining accepted-target | partial |
 | immutable split/run/reproducibility manifests | ADR 0013; ERD | `tepp_api` reproducibility manifest contract on protected main; `persistence_postgres` append-only SQL insert/lookup for `reproducibility_manifest`, `corpus_split_manifest`, `model_run`, and `model_artifact` (migration `0003`); full physical ERD constraints remaining | partial |
-| multilingual shared latent semantic space | PRD; ADR 0004 | future semantic/concept/topic crates | accepted-target |
+| multilingual shared latent semantic space | PRD; ADR 0004 | `measurement_invariance` configural/metric/scalar status and loading RMSE on the active PR; remaining language-profile alignment remains accepted-target | active-PR |
 | TRSL-TM temporal/relational topic posterior and backend compatibility | ADR 0012; ADR 0004 | future `topic_measurement` | accepted-target |
 | global P0 topic identity with activity/dormancy/reactivation | ADR 0012 | future topic lineage/activity state | accepted-target |
 | no default stopword deletion / no TF-IDF-BM25 inferential weighting | ADR 0004/0012; PRD/TRD | future semantic/method-source model | accepted-target |
diff --git a/docs/adr/0004-shared-multilingual-latent-space.md b/docs/adr/0004-shared-multilingual-latent-space.md
index c8da25b55..383f273ad 100644
--- a/docs/adr/0004-shared-multilingual-latent-space.md
+++ b/docs/adr/0004-shared-multilingual-latent-space.md
@@ -1,7 +1,7 @@
 # ADR 0004 — Shared multilingual latent semantic space
 
 **Decision status:** Accepted  
-**Implementation maturity:** accepted-target  
+**Implementation maturity:** active-PR — `measurement_invariance` records configural/metric/scalar status and refuses shared meaning from configural structure alone; remaining language-profile alignment remains accepted-target  
 **Date:** 2026-08-05  
 **Supersedes:** None. ADR 0012 governs the complete topic-estimator/backend/global-topic contract built on this multilingual measurement decision.
 
diff --git a/docs/adr/README.md b/docs/adr/README.md
index 1a9a7b315..506b22af9 100644
--- a/docs/adr/README.md
+++ b/docs/adr/README.md
@@ -9,7 +9,7 @@ Read [`ADR_POLICY.md`](ADR_POLICY.md) first. **Decision status and implementatio
 | [0001](0001-rust-first-modular-msa.md) | Rust-first numerical core and CPU `f64` reference | Accepted | partial | ADR 0011 owns cross-service/MSA authority; 0001 retains numerical/backend authority. |
 | [0002](0002-six-clock-temporal-semantics.md) | Six-clock temporal semantics and fail-closed historical leakage prevention | Accepted | active-PR | Unmerged PR #8 is the canonical Task 3 replacement implementing typed clocks/intervals against the current protected-main lineage; conflicted PR #5 is superseded lineage. Later graph/split enforcement remains target work. |
 | [0003](0003-relational-event-multiple-membership.md) | Relational event ontology and time-varying cross-classified multiple membership | Accepted | partial | Weighted time-varying membership network/roles are active-PR (PR #12); full multilevel estimators, graph ontology, and persistence remain accepted-target. ADR 0016 owns event-intelligence tasks. |
-| [0004](0004-shared-multilingual-latent-space.md) | One shared multilingual latent space with explicit invariance status | Accepted | accepted-target | ADR 0012 owns the full topic-estimator/backend/global-topic contract. |
+| [0004](0004-shared-multilingual-latent-space.md) | One shared multilingual latent space with explicit invariance status | Accepted | active-PR | Invariance status gates in `measurement_invariance` on the active PR; remaining language-profile alignment remains accepted-target. ADR 0012 owns the full topic-estimator contract. |
 | [0005](0005-posterior-esem-dsem.md) | Posterior-aware ESEM/DSEM and valid compositional coordinates | Accepted | accepted-target | Downstream psychometric authority; upstream topic/network model is clarified by ADR 0012. |
 | [0006](0006-vram-gpu-nvidia-orchestration.md) | VRAM-adaptive GPU compute and model-credential boundary | Accepted | accepted-target | LLM orchestration policy superseded by ADR 0010; autonomous development authority governed by ADR 0015. |
 | [0007](0007-rust-workspace-quality-gates.md) | Explicit Rust workspace, pinned toolchains, and exact quality gates | Accepted | implemented-main | ADR 0014 governs scientific/product claim promotion beyond repository-quality tooling. |
diff --git a/docs/research/measurement-invariance-status.md b/docs/research/measurement-invariance-status.md
new file mode 100644
index 000000000..2c6f0563b
--- /dev/null
+++ b/docs/research/measurement-invariance-status.md
@@ -0,0 +1,34 @@
+# Measurement invariance status (doctoring)
+
+## Scope
+
+`measurement_invariance` records an explicit configural, metric, or scalar
+status. Configural structure alone cannot license shared metric meaning.
+Recovered group loadings are scored with computed RMSE against known truth.
+
+This slice does not fit ESEM/DSEM, claim partial invariance, or treat a
+language profile as aligned from architecture alone.
+
+## Authority
+
+### Normative TEPP contract
+
+- `docs/adr/0004-shared-multilingual-latent-space.md` — equivalent meanings
+  must be aligned and tested for measurement invariance.
+- `docs/adr/0005-posterior-esem-dsem.md` — longitudinal invariance is a
+  psychometric requirement, not an implicit property of a shared space.
+
+### Supporting literature
+
+Meredith (1993) distinguishes configural, weak/metric, and strong/scalar
+invariance. Marsh et al. (2014) place those tests inside an ESEM program.
+They do **not** authorize treating configural similarity as shared scores.
+
+Meredith, W. (1993). Measurement invariance, factor analysis and factorial
+invariance. *Psychometrika, 58*(4), 525–543.
+https://doi.org/10.1007/BF02294825
+
+Marsh, H. W., Morin, A. J. S., Parker, P. D., & Kaur, G. (2014). Exploratory
+structural equation modeling: An integration of the best features of
+exploratory and confirmatory factor analysis. *Annual Review of Clinical
+Psychology, 10*, 85–110. https://doi.org/10.1146/annurev-clinpsy-032813-153700
diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md
index b4b144684..918173502 100644
--- a/docs/research/standards-and-literature.md
+++ b/docs/research/standards-and-literature.md
@@ -12,7 +12,9 @@ Asparouhov, T., & Muthén, B. (2009). Exploratory structural equation modeling.
 
 Marsh, H. W., Morin, A. J. S., Parker, P. D., & Kaur, G. (2014). Exploratory structural equation modeling: An integration of the best features of exploratory and confirmatory factor analysis. *Annual Review of Clinical Psychology, 10*, 85–110. https://doi.org/10.1146/annurev-clinpsy-032813-153700
 
-TEPP applies these sources to construct definition, score interpretation, reliability, validity evidence, uncertainty, consequences, longitudinal invariance, ESEM cross-loadings, and DSEM. Topic outputs are treated as fallible indicators or components only after their construct role is evaluated.
+Meredith, W. (1993). Measurement invariance, factor analysis and factorial invariance. *Psychometrika, 58*(4), 525–543. https://doi.org/10.1007/BF02294825
+
+TEPP applies these sources to construct definition, score interpretation, reliability, validity evidence, uncertainty, consequences, longitudinal invariance, ESEM cross-loadings, and DSEM. Topic outputs are treated as fallible indicators or components only after their construct role is evaluated. `measurement_invariance` records configural, metric, and scalar status and refuses shared metric meaning from configural structure alone.
 
 ## Structural, correlated, dynamic, relational, and multilingual topic models
 
diff --git a/docs/validation/temporal-event-foundation.md b/docs/validation/temporal-event-foundation.md
index e367a798f..1a16cd6ca 100644
--- a/docs/validation/temporal-event-foundation.md
+++ b/docs/validation/temporal-event-foundation.md
@@ -23,6 +23,7 @@ This report tracks exact-head scientific and engineering evidence required befor
 | Truth corpora / manifests | `tepp_simulation` | implemented-main | — | deterministic generator tests | Task 10 / PR #18 |
 | Recovery metrics | `validation_core` | implemented-main | — | RMSE/bias/coverage/MC gates | Task 11 / PR #19 |
 | Versioned API/export contracts | `tepp_api` | implemented-main | naruon HTTP interchange | unknown-field/version/limit + naruon HTTPS interchange tests | Task 12 / PR #21; live HTTP service remaining |
+| Measurement invariance status | `measurement_invariance` | active-PR | this PR | configural refusal + loading RMSE | ADR 0004/0005 |
 | CWL modular connectors | `docs/connectors/*` | implemented-main | — | contract docs + examples | PR #22; live HTTP ports remaining |
 | Release SBOM/provenance generator | `scripts/release_evidence.py` | partial | — | generate+validate in CI | Task 13 partial / PR #28 |
 
diff --git a/scripts/check_workspace_contract.py b/scripts/check_workspace_contract.py
index c7b1ecf58..615817d55 100644
--- a/scripts/check_workspace_contract.py
+++ b/scripts/check_workspace_contract.py
@@ -23,6 +23,7 @@
     "tepp_simulation",
     "validation_core",
     "tepp_api",
+    "measurement_invariance",
 )
 
 REQUIRED_CI_SNIPPETS: tuple[str, ...] = (