diff --git a/inbox/queue/.extraction-debug/2026-03-27-dario-amodei-urgency-interpretability.json b/inbox/queue/.extraction-debug/2026-03-27-dario-amodei-urgency-interpretability.json
new file mode 100644
index 00000000..2bd21e01
--- /dev/null
+++ b/inbox/queue/.extraction-debug/2026-03-27-dario-amodei-urgency-interpretability.json
@@ -0,0 +1,34 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "mechanistic-interpretability-addresses-behavioral-verification-failure-at-high-capability.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "interpretability-research-breakthrough-status-versus-governance-grade-application-timeline-gap.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 4,
+    "rejected": 2,
+    "fixes_applied": [
+      "mechanistic-interpretability-addresses-behavioral-verification-failure-at-high-capability.md:set_created:2026-03-28",
+      "mechanistic-interpretability-addresses-behavioral-verification-failure-at-high-capability.md:stripped_wiki_link:verification-degrades-faster-than-capability-grows",
+      "interpretability-research-breakthrough-status-versus-governance-grade-application-timeline-gap.md:set_created:2026-03-28",
+      "interpretability-research-breakthrough-status-versus-governance-grade-application-timeline-gap.md:stripped_wiki_link:AI-capability-and-reliability-are-independent-dimensions"
+    ],
+    "rejections": [
+      "mechanistic-interpretability-addresses-behavioral-verification-failure-at-high-capability.md:missing_attribution_extractor",
+      "interpretability-research-breakthrough-status-versus-governance-grade-application-timeline-gap.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-28"
+}
\ No newline at end of file
diff --git a/inbox/queue/2026-03-27-dario-amodei-urgency-interpretability.md b/inbox/queue/2026-03-27-dario-amodei-urgency-interpretability.md
index 69deb5e6..79156482 100644
--- a/inbox/queue/2026-03-27-dario-amodei-urgency-interpretability.md
+++ b/inbox/queue/2026-03-27-dario-amodei-urgency-interpretability.md
@@ -7,9 +7,12 @@ date: 2025-01-01
 domain: ai-alignment
 secondary_domains: []
 format: article
-status: unprocessed
+status: enrichment
 priority: medium
 tags: [interpretability, mechanistic-interpretability, alignment-verification, circuit-tracing, safety-evaluation, Anthropic, alignment-science, B1-evidence]
+processed_by: theseus
+processed_date: 2026-03-28
+extraction_model: "anthropic/claude-sonnet-4.5"
 ---
 
 ## Content
@@ -46,3 +49,9 @@ Key claims from the essay (based on search result excerpts and Anthropic's state
 PRIMARY CONNECTION: verification-degrades-faster-than-capability-grows — interpretability is the proposed technical solution; RSP v3.0 October 2026 timeline is the governance application
 WHY ARCHIVED: Grounds the interpretability urgency thesis in Anthropic's own intellectual framing; useful for evaluating whether October 2026 RSP commitment is achievable
 EXTRACTION HINT: The most useful claim is the gap between research progress (breakthrough technology designation) and governance-grade application (formal alignment threshold assessment by October 2026) — this may be a new form of benchmark-governance gap.
+
+
+## Key Facts
+- Anthropic released open-source attribution graph tools enabling circuit-level hypothesis testing
+- Anthropic stated goal to 'reliably detect most AI model problems by 2027' using interpretability tools
+- RSP v3.0 commits to 'systematic alignment assessments incorporating mechanistic interpretability' by October 2026