feat(research): kill switch technical report version 2

data/research.json

@@ -679,24 +679,40 @@
       "contribution": "An evaluator protocol that separates admission, drain, persistence, recovery and evidence at a tool gateway, with counterexamples to reading a signed refusal as proof of continuing shutdown.",
       "plain": "Pressing a kill switch, getting a signed refusal and seeing nothing further happen are three different things. Testing the cMCP gateway, the report finds that it refuses new work and stays blocked after a restart, but also that a call already admitted can finish and a tool reached directly, around the gateway, can still act. It proposes a way to evaluate shutdown that checks each of these separately, including a fresh check of whether the block holds now.",
       "limits": [
-        "Software-only and author operated, on one Windows host with software keys over loopback HTTP. No language model, confidential hardware or independently operated peer was used.",
+        "Software-only, on Windows hosts with software keys over loopback HTTP. The author and one external evaluator each controlled gateway and observer together; no language model, confidential hardware or independently operated peer was used.",
         "A direct path to the tool produced an effect while the gateway was stopped, which the gateway's records cannot show, and a call admitted before the trip still completed.",
         "A historical refusal still verifies after recovery: the receipt verifier accepts no challenge or maximum age, so present shutdown state needs a new observation."
       ],
-      "changes": "First public edition. Evaluates cMCP 9db65b5 and cA2A 540a578; results were repeated on September 27 and October 1, 2026 with the same outcomes, and later source was rechecked against main.",
       "origin": "Revises a discussion draft dated September 19, 2026.",
-      "evidence_note": "The author repeated every run on September 27 and October 1, 2026 in fresh environments at the pinned revisions. An independent evaluation is under way and will be reported in version 2.",
       "spec": "https://cmcp.agentrust-io.com/",
       "code": "https://github.com/agentrust-io/cmcp",
       "patent_pending": true,
-      "date": "2026-10-01",
-      "abstract": "A shutdown command, a signed refusal and the absence of subsequent effects are different observations. We examine those distinctions using the merged cMCP gateway kill switch and its accompanying policy-key and delegation revocation mechanisms. A reproducible evaluator drives gateway startup, signed agent identity, Cedar evaluation, loopback HTTP tool calls, durable blocks, process restart, recovery and offline receipt verification. The reference run satisfies 27 named assertions. Two targeted implementation weakenings are detected at their intended assertions. Separately, 81 existing cMCP component tests and 38 cA2A revocation tests pass on pinned source revisions. The observed system refuses new tool work through the stopped gateway and retains its block after restart. An admitted call can nevertheless finish during shutdown, a direct tool path can produce an effect while the gateway is stopped, and a historical refusal still verifies after recovery. These counterexamples establish the limits of treating a signed receipt as evidence of continuing or universal shutdown. We propose an evaluator protocol that separates admission, effects, persistence, recovery and freshness, with an explicit role for independent observation. The exercise uses software keys, one operator and no model or confidential hardware.",
-      "pages": 9,
-      "sha256": {
-        "paper.pdf": "d6703450646fd260a597165c56ee73d1f5b0531edcb366c4da51995b84a5dcf5",
-        "source.zip": "5204e01d837d74b50a44473de8bcb85a7da16efac6e884cbd74d63033afa9bb0"
-      },
-      "doi": "10.5281/zenodo.23091310"
+      "abstract": "A shutdown command, a signed refusal and the absence of subsequent effects are different observations. We examine those distinctions using the merged cMCP gateway kill switch and its accompanying policy-key and delegation revocation mechanisms. A reproducible evaluator drives gateway startup, signed agent identity, Cedar evaluation, loopback HTTP tool calls, durable blocks, process restart, recovery and offline receipt verification. The reference run satisfies 27 named assertions. Two targeted implementation weakenings are detected at their intended assertions. Separately, 81 existing cMCP component tests and 38 cA2A revocation tests pass on pinned source revisions. The observed system refuses new tool work through the stopped gateway and retains its block after restart. An admitted call can nevertheless finish during shutdown, a direct tool path can produce an effect while the gateway is stopped, and a historical refusal still verifies after recovery. These counterexamples establish the limits of treating a signed receipt as evidence of continuing or universal shutdown. An external evaluator repeated the reference run, both weakenings and both component suites on his own workstation and obtained the same outcome for every assertion. We propose an evaluator protocol that separates admission, effects, persistence, recovery and freshness, with an explicit role for independent observation. The exercise uses software keys, one operator and no model or confidential hardware.",
+      "versions": [
+        {
+          "version": 1,
+          "date": "2026-10-01",
+          "pages": 9,
+          "changes": "First public edition. Evaluates cMCP 9db65b5 and cA2A 540a578; results were repeated on September 27 and October 1, 2026 with the same outcomes, and later source was rechecked against main.",
+          "evidence_note": "The author repeated every run on September 27 and October 1, 2026 in fresh environments at the pinned revisions. An independent evaluation is under way and will be reported in version 2.",
+          "sha256": {
+            "paper.pdf": "d6703450646fd260a597165c56ee73d1f5b0531edcb366c4da51995b84a5dcf5",
+            "source.zip": "5204e01d837d74b50a44473de8bcb85a7da16efac6e884cbd74d63033afa9bb0"
+          },
+          "doi": "10.5281/zenodo.23091310"
+        },
+        {
+          "version": 2,
+          "date": "2026-10-11",
+          "pages": 11,
+          "changes": "Adds Section 9: an external evaluator, Zoheb Shaik, repeated the reference run, both weakenings and both component suites on his own workstation on October 11, 2026 with the same outcome for every assertion. Rechecks later source against current main. No version 1 result changes.",
+          "evidence_note": "One external evaluator repeated every run on his own workstation on October 11, 2026, with gateway and observer under his one administrator. One individual's evaluation, not a certification or ongoing verification.",
+          "sha256": {
+            "paper.pdf": "9ce0166a61e6225eabab67c42dd2e8a232c6cb499a566914e87df69fb9fb3023",
+            "source.zip": "d15611000995a4b3562dc2033a5a2454e5bc1f3a53d2d1930d53c9a52dca2594"
+          }
+        }
+      ]
     }
   ]
 }