diff --git a/PLAN.md b/PLAN.md
index 9008adc..7d08384 100644
--- a/PLAN.md
+++ b/PLAN.md
@@ -126,7 +126,7 @@ Wichtig:
   - track
   - present
   - record
-- Gemeinsame Arbitration-/Budget-Sicht für refinement/record/decode zentralisieren (Admission + Queue/Hold + Debug-Surface)
+- Gemeinsame Arbitration-/Budget-Sicht für refinement/record/decode zentralisieren (Admission + Queue/Hold + Debug-Surface) — umgesetzt via zentralem Arbiter im Pipeline-Paket + normalisierter Reason-Taxonomie; künftige Phase: tieferer Scheduler/Intent-Budget-Override
 
 ### F. Dokumentierte Betriebsprofile
 - initiale Profile definieren, z. B.:
diff --git a/README.md b/README.md
index a9bbeb1..6edcdcf 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ Edit `config.yaml` (autosave goes to `config.autosave.yaml`).
 - `resources.max_refinement_jobs` — processing budget hint
 - `resources.max_recording_streams` — recording/streaming budget hint
 - `resources.max_decode_jobs` — decode budget hint
-- `resources.decision_hold_ms` — baseline hold time for queue slots before churn (arbitration scales per profile/strategy)
+- `resources.decision_hold_ms` — baseline hold time for queue slots before churn (arbitration scales per profile/strategy and tags hold reasons in debug snapshots)
 - `profiles[]` — named operating profiles/intent metadata
 
 In phase 1, the engine stays backward compatible, but the config model now reflects the intended separation between:
@@ -95,7 +95,12 @@ In phase 1, the engine stays backward compatible, but the config model now refle
 - presentation
 - operator goals / future autonomous intent
 
-Refinement plans now rank candidates, while a shared arbitration step admits refinement/record/decode work based on budgets and hold policy.
+Refinement plans now rank candidates, while a shared arbitration step admits refinement/record/decode work based on budgets and hold policy. Arbitration reasons are normalized:
+- `refinement:*` for work item lifecycle (planned/admitted/running/completed/drop/skip)
+- `admission:*` for refinement admission outcomes
+- `decision:*` for record/decode decisions
+- `queue:*` when record/decode is deferred by budget
+Hold policy reasons are surfaced as `profile:*` / `strategy:*` tokens in `hold_source`.
 
 The long-term target is that you describe *what the system should do* (for example broad-span monitoring intent, preferred signal families, auto-record/decode priorities), while the engine decides *how* to allocate surveillance, refinement and decoding budgets.