docs(compliance): surface PRISMA-trAIce maturity caveat to users (#93) (#94)

Holst et al. (2025) self-describe their checklist as a "well-reasoned
albeit preliminary guideline" developed via systematic adaptation, not
a formal Delphi consensus study, with items "not yet empirically
validated across diverse research contexts." ARS adopted their tier
system and Mandatory-as-block decision but did not surface this
maturity context to users.

Two documentation-only changes, modeled on the disclosure pattern
already used by plagiarism_detection_protocol.md:

1. shared/prisma_trAIce_protocol.md — new "Status disclaimer" section
   after the existing Upstream sync warning, citing five verbatim
   Holst quotes and explaining why Mandatory-as-block is still
   defensible under the authors' own framing.

2. shared/agents/compliance_agent.md — new "Mandatory-block surface
   message" subsection requiring the block message to include a
   one-paragraph maturity note when a Mandatory tier item triggers
   block_decision = block. Block severity unchanged; this is
   informational disclosure only.

Scope intentionally limited to documentation surface. Issue #93
Item 3 (Schema 12 optional protocol_maturity field) is deferred to
a follow-up issue so it can go through schema-evolution discipline.

No changes to:
- tier semantics (Mandatory / HR / R / O)
- block_decision logic
- 17-item count or item definitions
- citation / freshness CI

Refs #93

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

shared/agents/compliance_agent.md

@@ -85,6 +85,14 @@ Items within each stage subset are independent and MAY be evaluated concurrently
 
 Multiple tier contributions aggregate using `max_severity` (see `compliance_checkpoint_protocol.md §Decision precedence`).
 
+### Mandatory-block surface message
+
+When a Mandatory-tier PRISMA-trAIce item triggers `block_decision = block`, the surfaced block message MUST include the following maturity note alongside the gap reason and override-ladder reference, so the user understands what authority is blocking them:
+
+> *Note: PRISMA-trAIce is currently a foundational proposal (Holst et al. 2025, *JMIR AI*, doi:[10.2196/80247](https://doi.org/10.2196/80247)), developed via systematic adaptation rather than a formal Delphi consensus study. Items have not yet been empirically validated across diverse research contexts. See `shared/prisma_trAIce_protocol.md` § Status disclaimer.*
+
+This note is informational only — it does not lower the block severity. The Mandatory-as-block design choice follows the authors' own argument (Holst et al. 2025) that non-transparent AI use is the higher-cost failure mode. Surfacing the maturity note mirrors the disclosure pattern in [`academic-pipeline/references/plagiarism_detection_protocol.md`](../../academic-pipeline/references/plagiarism_detection_protocol.md), which discloses heuristic-screening scope to the user.
+
 ## Self-check protocol
 
 Before finalising the report, the agent runs four self-checks. Any flagged check requires re-examination:

shared/prisma_trAIce_protocol.md

@@ -15,6 +15,14 @@ Verbatim snapshot of the 17-item PRISMA-trAIce checklist from the GitHub canonic
 
 > ⚠️ **Upstream sync warning.** If `cqh4046/PRISMA-trAIce` updates, a freshness CI check emits an annotation but does not block merges. Maintainers must manually re-sync this file and bump `snapshot_date` + `upstream_version_commit`. See `scripts/check_prisma_trAIce_freshness.py`.
 
+## Status disclaimer
+
+**PRISMA-trAIce is a foundational proposal, not a Delphi-consensus standard.** Holst et al. (2025) explicitly characterize their checklist as a "well-reasoned albeit preliminary guideline," developed via systematic adaptation of PRISMA 2020 rather than "a formal, broad-based Delphi study or consensus meeting," and note that the 17 items "have not yet been empirically validated across diverse research contexts." The authors frame PRISMA-trAIce as a "foundational proposal" and a "living standard" intended for the research community to "immediately adopt and refine."
+
+ARS adopts the authors' Mandatory / Highly Recommended / Recommended / Optional tier system as defined upstream, and treats Mandatory failures as Stage 2.5 / 4.5 blocks (per the Tier legend below). This block-on-Mandatory choice follows the authors' own argument that the risk of non-transparent AI use outweighs the risk of adopting a preliminary guideline. Future revisions of the upstream living standard are pulled in via the existing freshness CI (`scripts/check_prisma_trAIce_freshness.py`).
+
+> See Holst D, et al. JMIR AI. 2025. doi:[10.2196/80247](https://doi.org/10.2196/80247) — Discussion and Limitations sections.
+
 ## Tier legend
 
 | Tier | Behaviour when item FAILs |