From 248c5558606bdc5a5591a94ccdaae46fa9815ab0 Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Mon, 17 Aug 2026 21:35:31 +0900
Subject: [PATCH 1/7] feat(method): refuse prompt boilerplate as unique content

Instruction and prompt boilerplate stays explicit method structure
(ADR 0004 and 0012). It is not unique latent content and is not
erased by a stopword list. Recovery is the computed share of prompt
kinds that match known truth versus collapsing every token to unique
content.
---
 ARCHITECTURE.md                               |   1 +
 CHANGELOG.md                                  |   1 +
 Cargo.lock                                    |   4 +
 Cargo.toml                                    |   2 +
 README.md                                     |   3 +-
 crates/prompt_source/Cargo.toml               |  17 +++
 crates/prompt_source/src/error.rs             |  53 +++++++
 crates/prompt_source/src/kind.rs              | 132 ++++++++++++++++++
 crates/prompt_source/src/lib.rs               |  22 +++
 crates/prompt_source/tests/crate_contract.rs  |   7 +
 .../tests/prompt_source_contract.rs           |  67 +++++++++
 docs/TRACEABILITY.md                          |   2 +-
 .../0004-shared-multilingual-latent-space.md  |   2 +-
 ...ational-shared-latent-topic-measurement.md |   2 +-
 docs/adr/README.md                            |   4 +-
 docs/research/prompt-source-identity.md       |  31 ++++
 docs/research/standards-and-literature.md     |   4 +-
 docs/validation/temporal-event-foundation.md  |   1 +
 scripts/check_workspace_contract.py           |   1 +
 19 files changed, 349 insertions(+), 7 deletions(-)
 create mode 100644 crates/prompt_source/Cargo.toml
 create mode 100644 crates/prompt_source/src/error.rs
 create mode 100644 crates/prompt_source/src/kind.rs
 create mode 100644 crates/prompt_source/src/lib.rs
 create mode 100644 crates/prompt_source/tests/crate_contract.rs
 create mode 100644 crates/prompt_source/tests/prompt_source_contract.rs
 create mode 100644 docs/research/prompt-source-identity.md

diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index ffe514db..e365c4c7 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 |
+| `prompt_source` | prompt boilerplate is not unique latent content and not stopword deletion |
 
 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 3fe6d08d..70f6e478 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
 
+- `prompt_source` identity gate: instruction and prompt boilerplate is not unique latent content and is not erased by a stopword list; recovered prompt kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012).
 - `tepp_api` purpose-bound provider-payload minimization: time-bounded `PurposeGrant` evaluation, fail-closed expired/not-yet-valid/inverted/cross-tenant/impossible-calendar denial, semantic UTC calendar validation, refusal to copy identity mappings into model-provider payloads or ordinary logs, preservation of opaque analytical identifiers and membership roles (no blanket PII mask), a separately authorized scientific re-identification path, and an internally bound FIPS 180-4 SHA-256 audit digest appended through `ReidentificationAuditSink` before disclosure.
 - `persistence_postgres` retention/deletion/legal-hold (migration `0007`): policy rows, legal holds that block completed deletion, evidence tombstones without raw-source restore, analysis exclusion only for `logical_revocation`/`identity_tombstone` (not `cache_export_removal`), and deletion requests bound to the cited retention policy's tenant/class/purpose.
 - `persistence_postgres` backup/restore integrity: restored snapshots stay unusable until tenant, canonical `SHA-256`, knowledge-cutoff eligibility, temporal window order, and append-only triggers revalidate; SQL probes raise `restore integrity failed` (ADR 0013).
diff --git a/Cargo.lock b/Cargo.lock
index 616bfd78..eb8060e5 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -856,6 +856,10 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "prompt_source"
+version = "0.1.0"
+
 [[package]]
 name = "quote"
 version = "1.0.47"
diff --git a/Cargo.toml b/Cargo.toml
index 92565940..1a7cd1bc 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -11,6 +11,7 @@ members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/prompt_source",
 ]
 default-members = [
     "crates/evidence_core",
@@ -23,6 +24,7 @@ default-members = [
     "crates/tepp_simulation",
     "crates/validation_core",
     "crates/tepp_api",
+    "crates/prompt_source",
 ]
 
 [workspace.package]
diff --git a/README.md b/README.md
index ae74015d..67f75a1c 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/prompt_source
 ```
 
 ## Local verification
diff --git a/crates/prompt_source/Cargo.toml b/crates/prompt_source/Cargo.toml
new file mode 100644
index 00000000..9a48d6d0
--- /dev/null
+++ b/crates/prompt_source/Cargo.toml
@@ -0,0 +1,17 @@
+[package]
+name = "prompt_source"
+description = "Prompt boilerplate is not unique content and not stopword deletion."
+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/prompt_source/src/error.rs b/crates/prompt_source/src/error.rs
new file mode 100644
index 00000000..678cbbd1
--- /dev/null
+++ b/crates/prompt_source/src/error.rs
@@ -0,0 +1,53 @@
+//! Fail-closed prompt-source errors.
+
+use std::fmt;
+
+/// A fail-closed prompt-source error.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+#[non_exhaustive]
+pub enum PromptSourceError {
+    /// Prompt boilerplate was treated as unique latent content.
+    PromptIsNotUniqueContent,
+    /// Prompt boilerplate was treated as stopword deletion.
+    PromptIsNotStopwordDeletion,
+    /// A recovery slice was empty or length-mismatched.
+    InvalidPromptPayload,
+}
+
+impl fmt::Display for PromptSourceError {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let message = match self {
+            Self::PromptIsNotUniqueContent => "prompt boilerplate is not unique latent content",
+            Self::PromptIsNotStopwordDeletion => "prompt boilerplate is not stopword deletion",
+            Self::InvalidPromptPayload => "invalid prompt-source payload",
+        };
+        formatter.write_str(message)
+    }
+}
+
+impl std::error::Error for PromptSourceError {}
+
+#[cfg(test)]
+mod tests {
+    use super::PromptSourceError;
+
+    #[test]
+    fn error_messages_are_stable() {
+        for (error, message) in [
+            (
+                PromptSourceError::PromptIsNotUniqueContent,
+                "prompt boilerplate is not unique latent content",
+            ),
+            (
+                PromptSourceError::PromptIsNotStopwordDeletion,
+                "prompt boilerplate is not stopword deletion",
+            ),
+            (
+                PromptSourceError::InvalidPromptPayload,
+                "invalid prompt-source payload",
+            ),
+        ] {
+            assert_eq!(error.to_string(), message);
+        }
+    }
+}
diff --git a/crates/prompt_source/src/kind.rs b/crates/prompt_source/src/kind.rs
new file mode 100644
index 00000000..5bd9ba76
--- /dev/null
+++ b/crates/prompt_source/src/kind.rs
@@ -0,0 +1,132 @@
+//! Prompt boilerplate versus unique latent content.
+
+use crate::PromptSourceError;
+
+/// Closed vocabulary of prompt-related token treatments.
+#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+pub enum PromptKind {
+    /// Instruction or prompt boilerplate, not unique document meaning.
+    PromptBoilerplate,
+    /// Token treatment reserved for unique latent content.
+    UniqueContent,
+}
+
+impl PromptKind {
+    /// Return the stable wire kind name.
+    #[must_use]
+    pub const fn wire_name(self) -> &'static str {
+        match self {
+            Self::PromptBoilerplate => "prompt_boilerplate",
+            Self::UniqueContent => "unique_content",
+        }
+    }
+
+    /// Parse a stable wire kind name.
+    ///
+    /// # Errors
+    ///
+    /// Returns [`PromptSourceError::InvalidPromptPayload`] for unrecognized
+    /// names.
+    pub fn from_wire_name(name: &str) -> Result<Self, PromptSourceError> {
+        match name {
+            "prompt_boilerplate" => Ok(Self::PromptBoilerplate),
+            "unique_content" => Ok(Self::UniqueContent),
+            _ => Err(PromptSourceError::InvalidPromptPayload),
+        }
+    }
+}
+
+/// Refuse to treat prompt boilerplate as unique latent content.
+///
+/// # Errors
+///
+/// Returns [`PromptSourceError::PromptIsNotUniqueContent`] when `kind` is
+/// [`PromptKind::PromptBoilerplate`].
+pub fn refuse_prompt_as_unique_content(kind: PromptKind) -> Result<(), PromptSourceError> {
+    match kind {
+        PromptKind::PromptBoilerplate => Err(PromptSourceError::PromptIsNotUniqueContent),
+        PromptKind::UniqueContent => Ok(()),
+    }
+}
+
+/// Refuse to treat prompt boilerplate as stopword deletion.
+///
+/// # Errors
+///
+/// Returns [`PromptSourceError::PromptIsNotStopwordDeletion`] when `kind` is
+/// [`PromptKind::PromptBoilerplate`].
+pub fn refuse_prompt_as_stopword_deletion(kind: PromptKind) -> Result<(), PromptSourceError> {
+    match kind {
+        PromptKind::PromptBoilerplate => Err(PromptSourceError::PromptIsNotStopwordDeletion),
+        PromptKind::UniqueContent => Ok(()),
+    }
+}
+
+/// Fraction of recovered prompt kinds that match known truth.
+///
+/// # Errors
+///
+/// Returns [`PromptSourceError::InvalidPromptPayload`] when either slice is
+/// empty or the lengths differ.
+pub fn identity_recovery_rate(
+    truth: &[PromptKind],
+    decided: &[PromptKind],
+) -> Result<f64, PromptSourceError> {
+    if truth.is_empty() || truth.len() != decided.len() {
+        return Err(PromptSourceError::InvalidPromptPayload);
+    }
+    let mut matches = 0_u32;
+    for (truth_kind, decided_kind) in truth.iter().zip(decided) {
+        if truth_kind == decided_kind {
+            matches += 1;
+        }
+    }
+    Ok(f64::from(matches) / truth.len() as f64)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{
+        identity_recovery_rate, refuse_prompt_as_stopword_deletion,
+        refuse_prompt_as_unique_content, PromptKind,
+    };
+    use crate::PromptSourceError;
+
+    #[test]
+    fn local_branches_cover_kinds_payloads_and_wire_names() {
+        assert_eq!(
+            refuse_prompt_as_unique_content(PromptKind::PromptBoilerplate),
+            Err(PromptSourceError::PromptIsNotUniqueContent)
+        );
+        assert_eq!(
+            refuse_prompt_as_stopword_deletion(PromptKind::PromptBoilerplate),
+            Err(PromptSourceError::PromptIsNotStopwordDeletion)
+        );
+        refuse_prompt_as_unique_content(PromptKind::UniqueContent).expect("unique");
+        refuse_prompt_as_stopword_deletion(PromptKind::UniqueContent).expect("unique");
+        for kind in [PromptKind::PromptBoilerplate, PromptKind::UniqueContent] {
+            assert_eq!(
+                PromptKind::from_wire_name(kind.wire_name()).expect("round-trip"),
+                kind
+            );
+        }
+        assert_eq!(
+            PromptKind::from_wire_name("template"),
+            Err(PromptSourceError::InvalidPromptPayload)
+        );
+        let matched = identity_recovery_rate(
+            &[PromptKind::PromptBoilerplate],
+            &[PromptKind::PromptBoilerplate],
+        )
+        .expect("rate");
+        assert!((matched - 1.0).abs() < f64::EPSILON);
+        assert_eq!(
+            identity_recovery_rate(&[], &[]),
+            Err(PromptSourceError::InvalidPromptPayload)
+        );
+        assert_eq!(
+            identity_recovery_rate(&[PromptKind::PromptBoilerplate], &[]),
+            Err(PromptSourceError::InvalidPromptPayload)
+        );
+    }
+}
diff --git a/crates/prompt_source/src/lib.rs b/crates/prompt_source/src/lib.rs
new file mode 100644
index 00000000..f3e070f2
--- /dev/null
+++ b/crates/prompt_source/src/lib.rs
@@ -0,0 +1,22 @@
+#![forbid(unsafe_code)]
+#![deny(missing_docs)]
+#![allow(clippy::cast_precision_loss)]
+//! Prompt boilerplate is not unique latent content.
+//!
+//! Instruction and prompt text stays explicit method structure. It is not
+//! unique document meaning and is not erased by a stopword list
+//! (ADR 0004/0012).
+
+mod error;
+mod kind;
+
+/// Fail-closed prompt-source errors.
+pub use error::PromptSourceError;
+/// Fraction of recovered prompt kinds that match known truth.
+pub use kind::identity_recovery_rate;
+/// Refuse to treat prompt boilerplate as stopword deletion.
+pub use kind::refuse_prompt_as_stopword_deletion;
+/// Refuse to treat prompt boilerplate as unique latent content.
+pub use kind::refuse_prompt_as_unique_content;
+/// Closed vocabulary of prompt-related token treatments.
+pub use kind::PromptKind;
diff --git a/crates/prompt_source/tests/crate_contract.rs b/crates/prompt_source/tests/crate_contract.rs
new file mode 100644
index 00000000..7f82bf4d
--- /dev/null
+++ b/crates/prompt_source/tests/crate_contract.rs
@@ -0,0 +1,7 @@
+//! Integration contract for the `prompt_source` package identity.
+
+#[test]
+fn package_identity_is_stable() {
+    let observed = std::hint::black_box(env!("CARGO_PKG_NAME"));
+    assert_eq!(observed, "prompt_source");
+}
diff --git a/crates/prompt_source/tests/prompt_source_contract.rs b/crates/prompt_source/tests/prompt_source_contract.rs
new file mode 100644
index 00000000..bce40e3e
--- /dev/null
+++ b/crates/prompt_source/tests/prompt_source_contract.rs
@@ -0,0 +1,67 @@
+//! Prompt boilerplate is not unique content and not stopword deletion.
+
+use prompt_source::{
+    identity_recovery_rate, refuse_prompt_as_stopword_deletion, refuse_prompt_as_unique_content,
+    PromptKind, PromptSourceError,
+};
+
+#[test]
+fn prompt_boilerplate_cannot_become_unique_content_or_stopword_deletion() {
+    assert_eq!(
+        refuse_prompt_as_unique_content(PromptKind::PromptBoilerplate),
+        Err(PromptSourceError::PromptIsNotUniqueContent)
+    );
+    assert_eq!(
+        refuse_prompt_as_stopword_deletion(PromptKind::PromptBoilerplate),
+        Err(PromptSourceError::PromptIsNotStopwordDeletion)
+    );
+    refuse_prompt_as_unique_content(PromptKind::UniqueContent).expect("unique");
+    refuse_prompt_as_stopword_deletion(PromptKind::UniqueContent).expect("unique");
+}
+
+#[test]
+fn recovered_kinds_match_known_truth_better_than_a_unique_content_collapse() {
+    let truth = [
+        PromptKind::PromptBoilerplate,
+        PromptKind::UniqueContent,
+        PromptKind::PromptBoilerplate,
+    ];
+    let recovered = truth;
+    let collapsed = [
+        PromptKind::UniqueContent,
+        PromptKind::UniqueContent,
+        PromptKind::UniqueContent,
+    ];
+    let recovered_rate = identity_recovery_rate(&truth, &recovered).expect("recovered");
+    let collapsed_rate = identity_recovery_rate(&truth, &collapsed).expect("collapsed");
+    let expected = {
+        let mut matches = 0_u32;
+        for (truth_kind, decided_kind) in truth.iter().zip(recovered.iter()) {
+            if truth_kind == decided_kind {
+                matches += 1;
+            }
+        }
+        f64::from(matches) / f64::from(u32::try_from(truth.len()).expect("len"))
+    };
+    assert!((recovered_rate - expected).abs() < f64::EPSILON);
+    assert!(recovered_rate > collapsed_rate);
+}
+
+#[test]
+fn empty_or_mismatched_kind_payloads_fail_closed() {
+    assert_eq!(
+        identity_recovery_rate(&[], &[]),
+        Err(PromptSourceError::InvalidPromptPayload)
+    );
+    assert_eq!(
+        identity_recovery_rate(&[PromptKind::PromptBoilerplate], &[]),
+        Err(PromptSourceError::InvalidPromptPayload)
+    );
+    assert_eq!(
+        identity_recovery_rate(
+            &[PromptKind::PromptBoilerplate, PromptKind::UniqueContent],
+            &[PromptKind::PromptBoilerplate]
+        ),
+        Err(PromptSourceError::InvalidPromptPayload)
+    );
+}
diff --git a/docs/TRACEABILITY.md b/docs/TRACEABILITY.md
index dfcdd9e8..8ea301c2 100644
--- a/docs/TRACEABILITY.md
+++ b/docs/TRACEABILITY.md
@@ -25,7 +25,7 @@ The full APA 7th standards/literature register remains `docs/research/standards-
 | 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 |
-| report template/section/copied/style/modality method effects | ADR 0004/0012; PRD/TRD | simulation truth factors implemented; estimator-side method model remains future | partial |
+| report template/section/copied/style/modality method effects | ADR 0004/0012; PRD/TRD | simulation truth factors implemented; `prompt_source` prompt-versus-unique-content identity on the active PR; estimator-side method model remains future | partial |
 | candidate K statistical/Pareto gates + blinded LLM review | ADR 0012; research | future `model_selection` | accepted-target |
 | compositional topic correlation / stable clustering | ADR 0005/0012; research | future `network_analysis` | accepted-target |
 | posterior ESEM / longitudinal invariance / DSEM | ADR 0005 | future `psychometric_core` | accepted-target |
diff --git a/docs/adr/0004-shared-multilingual-latent-space.md b/docs/adr/0004-shared-multilingual-latent-space.md
index c8da25b5..2ca03cbc 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:** accepted-target — prompt-versus-unique-content identity in `prompt_source` on the active PR; shared-space estimators remain 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/0012-temporal-relational-shared-latent-topic-measurement.md b/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md
index c3d5085f..671140a3 100644
--- a/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md
+++ b/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md
@@ -1,7 +1,7 @@
 # ADR 0012 — Temporal Relational Shared-Latent Topic Measurement
 
 **Decision status:** Accepted  
-**Implementation maturity:** accepted-target  
+**Implementation maturity:** accepted-target — prompt-versus-unique-content identity in `prompt_source` on the active PR; estimator-side method model remains accepted-target  
 **Date:** 2026-08-12  
 **Supersedes:** None; refines ADR 0004 and ADR 0005 without replacing their multilingual and psychometric authorities.
 
diff --git a/docs/adr/README.md b/docs/adr/README.md
index f16c2345..54913cba 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 | accepted-target | Prompt-versus-unique-content identity is `prompt_source` on the active PR; 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. |
@@ -17,7 +17,7 @@ Read [`ADR_POLICY.md`](ADR_POLICY.md) first. **Decision status and implementatio
 | [0009](0009-purpose-bound-pii-governance.md) | Purpose-bound PII governance without blanket masking | Accepted | partial | Persistence retention/deletion/legal-hold (`0007`) implemented-main; provider-payload minimization and elevated re-identification are on the active PR; deployment evidence remains accepted-target. |
 | [0010](0010-adaptive-llm-orchestration.md) | Adaptive LLM orchestration and test-time compute | Accepted | accepted-target | Owns direct/verify/committee/conductor selection, budget, role/topology, and ablation policy. |
 | [0011](0011-standalone-modular-msa-boundary.md) | Standalone operation and modular CWL MSA boundary | Accepted | partial | Owns cross-service persistence/credential/API authority; no direct cross-service application-table coupling. |
-| [0012](0012-temporal-relational-shared-latent-topic-measurement.md) | Temporal Relational Shared-Latent Topic Measurement (TRSL-TM) | Accepted | accepted-target | Owns topic backend compatibility, global topic identity, method effects, K/model-selection prerequisites, and compositional topic coordinates. |
+| [0012](0012-temporal-relational-shared-latent-topic-measurement.md) | Temporal Relational Shared-Latent Topic Measurement (TRSL-TM) | Accepted | accepted-target | Prompt-versus-unique-content identity is `prompt_source` on the active PR; estimator-side method model, backend, and K gates remain accepted-target. |
 | [0013](0013-bitemporal-persistence-reproducibility-and-split-authority.md) | Bitemporal persistence, reproducibility manifests, and relation-aware split authority | Accepted | partial | Owns PostgreSQL adapter semantics, immutable run/split manifests, leakage-safe partitions, and recovery identity; optional `live-sqlx` `PgPool`, live PG CI, tenant RLS, and `0006` membership implemented-main; `0007` retention/deletion/legal-hold on the active PR; remaining physical ERD/backup accepted-target. |
 | [0014](0014-scientific-claim-promotion-and-release-evidence.md) | Scientific claim promotion and release evidence authority | Accepted | partial | Separates design, implementation, scientific/product claim, and release authority; repository SBOM/provenance generator implemented, full release bundle remaining. |
 | [0015](0015-autonomous-development-review-and-merge-authority.md) | Autonomous development, review, and merge authority separation | Accepted | active-PR | Separates model proposal, deterministic verification, publication, independent review, and merge/release authority. |
diff --git a/docs/research/prompt-source-identity.md b/docs/research/prompt-source-identity.md
new file mode 100644
index 00000000..f35acb2b
--- /dev/null
+++ b/docs/research/prompt-source-identity.md
@@ -0,0 +1,31 @@
+# Prompt boilerplate is not unique content (doctoring)
+
+## Scope
+
+`prompt_source` keeps instruction and prompt boilerplate out of unique
+latent content and out of global stopword deletion. Recovery is the
+computed share of recovered kinds that match known truth.
+
+This slice does not persist method sources, allocate migration `0008`,
+or replace `method_effects`, `section_source`, `style_source`,
+`copied_text`, `modality_source`, `corpus_background`, or
+`stopword_deletion`.
+
+## Authority
+
+### Normative TEPP contract
+
+- `docs/adr/0004-shared-multilingual-latent-space.md` and
+  `docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md`
+  — method and template sources are modeled explicitly and are not
+  inferential topic weights or stopword deletions.
+
+### Supporting literature
+
+Liu et al. (2023) treat prompting as a method condition that shapes
+emissions. Prompt text is not the document's unique latent meaning.
+
+Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023).
+Pre-train, prompt, and predict: A systematic survey of prompting methods
+in natural language processing. *ACM Computing Surveys, 55*(9), Article
+195. https://doi.org/10.1145/3560815
diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md
index 6e0438fe..e8911e14 100644
--- a/docs/research/standards-and-literature.md
+++ b/docs/research/standards-and-literature.md
@@ -32,7 +32,9 @@ Bianchi, F., Terragni, S., Hovy, D., Nozza, D., & Fersini, E. (2021). Cross-ling
 
 Nguyen, T. P., Minh, N. V., Nguyen, T., Van, L. N., Nguyen, D. A., Sang, D. V., & Le, T. (2025). XTRA: Cross-lingual topic modeling with topic and representation alignments. In *Findings of the Association for Computational Linguistics: EMNLP 2025*. Association for Computational Linguistics.
 
-TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts.
+Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. *ACM Computing Surveys, 55*(9), Article 195. https://doi.org/10.1145/3560815
+
+TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. Instruction and prompt boilerplate is modeled as explicit method structure, not unique latent content and not a stopword deletion (Liu et al., 2023).
 
 ## Topic-model evaluation and LLM judges
 
diff --git a/docs/validation/temporal-event-foundation.md b/docs/validation/temporal-event-foundation.md
index 7c50db23..7560c166 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 |
+| Prompt-versus-unique-content identity | `prompt_source` | accepted-target | active PR | refuse prompt-as-unique/stopword + recovery vs unique-content collapse | ADR 0004/0012 |
 | Purpose-bound provider payloads | `tepp_api` | active-PR | provider-payload minimization | expired/not-yet-valid/inverted/cross-tenant/impossible-calendar grant, mapping refusal, audited elevated re-id replay | ADR 0009; `docs/research/provider-payload-minimization.md` |
 | 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 c7b1ecf5..3b810361 100644
--- a/scripts/check_workspace_contract.py
+++ b/scripts/check_workspace_contract.py
@@ -23,6 +23,7 @@
     "tepp_simulation",
     "validation_core",
     "tepp_api",
+    "prompt_source",
 )
 
 REQUIRED_CI_SNIPPETS: tuple[str, ...] = (

From 5319e0ca0baa581fb7890b51e38e638aae4dc69b Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Fri, 21 Aug 2026 02:52:13 +0900
Subject: [PATCH 2/7] fix(prompt-source): apply repository rustfmt

---
 crates/prompt_source/src/kind.rs                     | 4 ++--
 crates/prompt_source/src/lib.rs                      | 4 ++--
 crates/prompt_source/tests/prompt_source_contract.rs | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/crates/prompt_source/src/kind.rs b/crates/prompt_source/src/kind.rs
index 5bd9ba76..ad3d09d7 100644
--- a/crates/prompt_source/src/kind.rs
+++ b/crates/prompt_source/src/kind.rs
@@ -87,8 +87,8 @@ pub fn identity_recovery_rate(
 #[cfg(test)]
 mod tests {
     use super::{
-        identity_recovery_rate, refuse_prompt_as_stopword_deletion,
-        refuse_prompt_as_unique_content, PromptKind,
+        PromptKind, identity_recovery_rate, refuse_prompt_as_stopword_deletion,
+        refuse_prompt_as_unique_content,
     };
     use crate::PromptSourceError;
 
diff --git a/crates/prompt_source/src/lib.rs b/crates/prompt_source/src/lib.rs
index f3e070f2..8f8893f4 100644
--- a/crates/prompt_source/src/lib.rs
+++ b/crates/prompt_source/src/lib.rs
@@ -12,11 +12,11 @@ mod kind;
 
 /// Fail-closed prompt-source errors.
 pub use error::PromptSourceError;
+/// Closed vocabulary of prompt-related token treatments.
+pub use kind::PromptKind;
 /// Fraction of recovered prompt kinds that match known truth.
 pub use kind::identity_recovery_rate;
 /// Refuse to treat prompt boilerplate as stopword deletion.
 pub use kind::refuse_prompt_as_stopword_deletion;
 /// Refuse to treat prompt boilerplate as unique latent content.
 pub use kind::refuse_prompt_as_unique_content;
-/// Closed vocabulary of prompt-related token treatments.
-pub use kind::PromptKind;
diff --git a/crates/prompt_source/tests/prompt_source_contract.rs b/crates/prompt_source/tests/prompt_source_contract.rs
index bce40e3e..966976ec 100644
--- a/crates/prompt_source/tests/prompt_source_contract.rs
+++ b/crates/prompt_source/tests/prompt_source_contract.rs
@@ -1,8 +1,8 @@
 //! Prompt boilerplate is not unique content and not stopword deletion.
 
 use prompt_source::{
-    identity_recovery_rate, refuse_prompt_as_stopword_deletion, refuse_prompt_as_unique_content,
-    PromptKind, PromptSourceError,
+    PromptKind, PromptSourceError, identity_recovery_rate, refuse_prompt_as_stopword_deletion,
+    refuse_prompt_as_unique_content,
 };
 
 #[test]

From c5fb37d9855a0df97bee899e5c31a8e3d2bc9801 Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Fri, 21 Aug 2026 05:07:44 +0900
Subject: [PATCH 3/7] test(quality): derive docstring crate count from
 workspace contract

---
 tests/quality/test_check_docstrings.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/quality/test_check_docstrings.py b/tests/quality/test_check_docstrings.py
index 2c11f7a5..da59f799 100644
--- a/tests/quality/test_check_docstrings.py
+++ b/tests/quality/test_check_docstrings.py
@@ -11,6 +11,7 @@
 from unittest import mock
 
 from scripts import check_docstrings as docstrings
+from scripts import check_workspace_contract as workspace_contract
 
 
 REPOSITORY_ROOT = Path(__file__).resolve().parents[2]
@@ -24,7 +25,7 @@ def test_live_repository_is_documented(self) -> None:
 
         sources = docstrings.rust_sources(REPOSITORY_ROOT)
         crate_roots = sorted(REPOSITORY_ROOT.glob("crates/*/src/lib.rs"))
-        self.assertEqual(len(crate_roots), 10)
+        self.assertEqual(len(crate_roots), len(workspace_contract.EXPECTED_CRATES))
         self.assertTrue(set(crate_roots).issubset(sources))
         self.assertGreaterEqual(len(sources), len(crate_roots))
         self.assertEqual(docstrings.validate_repository(REPOSITORY_ROOT), [])

From 9409d83d29e7fca707e5833ae025550f9d09a65f Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Fri, 21 Aug 2026 05:37:35 +0900
Subject: [PATCH 4/7] docs: remove duplicate provider payload ledger row

---
 docs/validation/temporal-event-foundation.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/docs/validation/temporal-event-foundation.md b/docs/validation/temporal-event-foundation.md
index 471eb315..80dadcad 100644
--- a/docs/validation/temporal-event-foundation.md
+++ b/docs/validation/temporal-event-foundation.md
@@ -24,7 +24,6 @@ This report tracks exact-head scientific and engineering evidence required befor
 | 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 |
 | Prompt-versus-unique-content identity | `prompt_source` | accepted-target | active PR | refuse prompt-as-unique/stopword + recovery vs unique-content collapse | ADR 0004/0012 |
-| Purpose-bound provider payloads | `tepp_api` | active-PR | provider-payload minimization | expired/not-yet-valid/inverted/cross-tenant/impossible-calendar grant, mapping refusal, audited elevated re-id replay | ADR 0009; `docs/research/provider-payload-minimization.md` |
 | Purpose-bound provider payloads | `tepp_api` | implemented-main | provider-payload minimization | expired/not-yet-valid/inverted/cross-tenant/impossible-calendar grant, mapping refusal, audited elevated re-id replay | ADR 0009; `docs/research/provider-payload-minimization.md` |
 | Adaptive orchestration router | `tepp_api` | accepted-target | active PR | mode selection, document-control denial, ablation, credential-free bind | ADR 0010; `docs/research/adaptive-orchestration-router.md` |
 | CWL modular connectors | `docs/connectors/*` | implemented-main | — | contract docs + examples | PR #22; live HTTP ports remaining |

From a67d90381d62ccb2a094fca2f722e729761cbd53 Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Fri, 21 Aug 2026 06:27:37 +0900
Subject: [PATCH 5/7] docs(prompt): bound identity claim to repository policy

---
 CHANGELOG.md                              | 2 +-
 docs/research/prompt-source-identity.md   | 7 +++++--
 docs/research/standards-and-literature.md | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6f2c00c6..3240d3fc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,7 +6,7 @@ All notable changes to TEPP are documented here. The format follows Keep a Chang
 
 ### Added
 
-- `prompt_source` identity gate: instruction and prompt boilerplate is not unique latent content and is not erased by a stopword list; recovered prompt kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012).
+- `prompt_source` identity gate: instruction and prompt boilerplate is not unique latent content and is not erased by a stopword list; on the mixed known-truth fixture, recovered prompt kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012).
 - `tepp_api` adaptive orchestration router (ADR 0010): versioned `direct`/`verify`/`committee`/`conductor`/`abstain` selection from CPU `f64` risk, ambiguity, evidence, and token-budget inputs; recorded stages, recursion, decomposition, access lists, and role-specific reasoning effort; fail-closed document-controlled policy/access/credentials; LLM plans remain proposals under deterministic statistical authority; comparable-budget ablation requires a direct baseline; credential-free contextual-orchestrator binding. Live NIM HTTP remains accepted-target.
 - `tepp_api` purpose-bound provider-payload minimization: time-bounded `PurposeGrant` evaluation, fail-closed expired/not-yet-valid/inverted/cross-tenant/impossible-calendar denial, semantic UTC calendar validation, refusal to copy identity mappings into model-provider payloads or ordinary logs, preservation of opaque analytical identifiers and membership roles (no blanket PII mask), a separately authorized scientific re-identification path, and an internally bound FIPS 180-4 SHA-256 audit digest appended through `ReidentificationAuditSink` before disclosure.
 - `persistence_postgres` backup/restore integrity: restored snapshots stay unusable until tenant, canonical `SHA-256`, knowledge-cutoff eligibility, temporal window order, and append-only triggers revalidate; SQL probes raise `restore integrity failed` (ADR 0013).
diff --git a/docs/research/prompt-source-identity.md b/docs/research/prompt-source-identity.md
index f35acb2b..fe329fc6 100644
--- a/docs/research/prompt-source-identity.md
+++ b/docs/research/prompt-source-identity.md
@@ -22,8 +22,11 @@ or replace `method_effects`, `section_source`, `style_source`,
 
 ### Supporting literature
 
-Liu et al. (2023) treat prompting as a method condition that shapes
-emissions. Prompt text is not the document's unique latent meaning.
+Liu et al. (2023) is retained as a secondary survey of prompting methods and
+is not used as evidence for the repository's latent-content classification.
+The statement that prompt boilerplate is not unique latent content is a
+normative TEPP measurement contract derived from ADR 0004 and ADR 0012, not a
+universal empirical claim about every prompt or corpus.
 
 Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023).
 Pre-train, prompt, and predict: A systematic survey of prompting methods
diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md
index a5ff2048..e1612e5a 100644
--- a/docs/research/standards-and-literature.md
+++ b/docs/research/standards-and-literature.md
@@ -34,7 +34,7 @@ Nguyen, T. P., Minh, N. V., Nguyen, T., Van, L. N., Nguyen, D. A., Sang, D. V.,
 
 Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. *ACM Computing Surveys, 55*(9), Article 195. https://doi.org/10.1145/3560815
 
-TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. Instruction and prompt boilerplate is modeled as explicit method structure, not unique latent content and not a stopword deletion (Liu et al., 2023).
+TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. As a normative ADR 0004/0012 contract, instruction and prompt boilerplate is modeled as explicit method structure, not unique latent content and not a stopword deletion. Liu et al. (2023) remains secondary background on prompting methods, not empirical support for that repository-specific classification.
 
 ## Topic-model evaluation and LLM judges
 

From 70a6c6608e39df757417b2674f0acf27aa09b612 Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Fri, 21 Aug 2026 11:04:04 +0900
Subject: [PATCH 6/7] docs: narrow prompt identity evidence claims

---
 CHANGELOG.md                              |  2 +-
 docs/research/prompt-source-identity.md   | 29 +++++++++++++++--------
 docs/research/standards-and-literature.md |  6 ++++-
 3 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9c10a794..3c3be4ca 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,7 +6,7 @@ All notable changes to TEPP are documented here. The format follows Keep a Chang
 
 ### Added
 
-- `prompt_source` identity gate: instruction and prompt boilerplate is not unique latent content and is not erased by a stopword list; on the mixed known-truth fixture, recovered prompt kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012).
+- `prompt_source` identity gate: instruction and prompt boilerplate is not unique latent content and is not erased by a stopword list; `identity_recovery_rate` reports exact kind matches, with a contract test comparing correct recovery with an all-unique collapse on a mixed known-truth fixture (ADR 0004/0012).
 - `tepp_api` naruon live loopback HTTP/1.1 listener: `serve_one` installs a read/write deadline, requires a loopback `Host`, refuses `Transfer-Encoding` and NIM/proxy credential headers, parses `knowledge_cutoff` as RFC 3339 and refuses a future cutoff, keys analysis-run idempotency by tenant plus key, and proves both analysis-run and export POSTs over a real `TcpStream`. Not a production TLS/`$PORT` service (ADR 0011).
 - `tepp_api` adaptive orchestration router (ADR 0010): versioned `direct`/`verify`/`committee`/`conductor`/`abstain` selection from CPU `f64` risk, ambiguity, evidence, and token-budget inputs; recorded stages, recursion, decomposition, access lists, and role-specific reasoning effort; fail-closed document-controlled policy/access/credentials; LLM plans remain proposals under deterministic statistical authority; comparable-budget ablation requires a direct baseline; credential-free contextual-orchestrator binding. Live NIM HTTP remains accepted-target.
 - `tepp_api` purpose-bound provider-payload minimization: time-bounded `PurposeGrant` evaluation, fail-closed expired/not-yet-valid/inverted/cross-tenant/impossible-calendar denial, semantic UTC calendar validation, refusal to copy identity mappings into model-provider payloads or ordinary logs, preservation of opaque analytical identifiers and membership roles (no blanket PII mask), a separately authorized scientific re-identification path, and an internally bound FIPS 180-4 SHA-256 audit digest appended through `ReidentificationAuditSink` before disclosure.
diff --git a/docs/research/prompt-source-identity.md b/docs/research/prompt-source-identity.md
index fe329fc6..884ca696 100644
--- a/docs/research/prompt-source-identity.md
+++ b/docs/research/prompt-source-identity.md
@@ -22,13 +22,22 @@ or replace `method_effects`, `section_source`, `style_source`,
 
 ### Supporting literature
 
-Liu et al. (2023) is retained as a secondary survey of prompting methods and
-is not used as evidence for the repository's latent-content classification.
-The statement that prompt boilerplate is not unique latent content is a
-normative TEPP measurement contract derived from ADR 0004 and ADR 0012, not a
-universal empirical claim about every prompt or corpus.
-
-Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023).
-Pre-train, prompt, and predict: A systematic survey of prompting methods
-in natural language processing. *ACM Computing Surveys, 55*(9), Article
-195. https://doi.org/10.1145/3560815
+Brown et al. (2020) provide primary evidence that textual prompts and
+demonstrations condition language-model task behavior, while Reynolds and
+McDonell (2021) study prompt programming as a method for directing model
+behavior. Neither study defines TEPP's latent-content labels. The statement
+that prompt boilerplate is not unique latent content is therefore a normative
+TEPP measurement contract derived from ADR 0004 and ADR 0012, not a universal
+empirical claim about every prompt or corpus.
+
+Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P.,
+Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss,
+A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J.,
+Winter, C., … Amodei, D. (2020). Language models are few-shot learners.
+*Advances in Neural Information Processing Systems, 33*, 1877–1901.
+https://papers.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
+
+Reynolds, L., & McDonell, K. (2021). Prompt programming for large language
+models: Beyond the few-shot paradigm. In *Extended abstracts of the 2021 CHI
+conference on human factors in computing systems*. Association for Computing
+Machinery. https://doi.org/10.1145/3411763.3451760
diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md
index a14dc6f7..d32a3ad1 100644
--- a/docs/research/standards-and-literature.md
+++ b/docs/research/standards-and-literature.md
@@ -32,9 +32,13 @@ Bianchi, F., Terragni, S., Hovy, D., Nozza, D., & Fersini, E. (2021). Cross-ling
 
 Nguyen, T. P., Minh, N. V., Nguyen, T., Van, L. N., Nguyen, D. A., Sang, D. V., & Le, T. (2025). XTRA: Cross-lingual topic modeling with topic and representation alignments. In *Findings of the Association for Computational Linguistics: EMNLP 2025*. Association for Computational Linguistics.
 
+Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. *Advances in Neural Information Processing Systems, 33*, 1877–1901. https://papers.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
+
+Reynolds, L., & McDonell, K. (2021). Prompt programming for large language models: Beyond the few-shot paradigm. In *Extended abstracts of the 2021 CHI conference on human factors in computing systems*. Association for Computing Machinery. https://doi.org/10.1145/3411763.3451760
+
 Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. *ACM Computing Surveys, 55*(9), Article 195. https://doi.org/10.1145/3560815
 
-TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. As a normative ADR 0004/0012 contract, instruction and prompt boilerplate is modeled as explicit method structure, not unique latent content and not a stopword deletion. Liu et al. (2023) remains secondary background on prompting methods, not empirical support for that repository-specific classification.
+TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. Brown et al. (2020) and Reynolds and McDonell (2021) provide primary research context for prompts as task-conditioning and prompt-programming mechanisms; they do not define TEPP's latent-content labels. As a normative ADR 0004/0012 contract, instruction and prompt boilerplate is therefore modeled as explicit method structure, not unique latent content and not a stopword deletion. Liu et al. (2023) is secondary survey background only and is not evidence for that repository-specific classification.
 
 ## Topic-model evaluation and LLM judges
 

From c1bd092d1319728c9dbdf4be744eb0e795d98207 Mon Sep 17 00:00:00 2001
From: Seongho Bae <me@seonghobae.me>
Date: Mon, 24 Aug 2026 18:50:43 +0900
Subject: [PATCH 7/7] chore: regenerate Cargo.lock after main merge

---
 Cargo.lock | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Cargo.lock b/Cargo.lock
index fcd7b90e..656738e2 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1101,6 +1101,10 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "prompt_source"
+version = "0.1.0"
+
 [[package]]
 name = "provider_receipt"
 version = "0.1.0"