audrey 1.1.2 → 1.1.3

package/docs/paper/output/arxiv/main.tex

@@ -731,14 +731,14 @@ These numbers measure Audrey's local call path under an in-process mock embeddin
 
 \subsection{Behavioral Regression Result}
 
-The current \texttt{benchmarks/output/summary.json} was generated on 2026-07-13T14:48:45.265Z with command \texttt{node benchmarks/run.js --provider mock --dimensions 64} (Ledger: E24). It reports:
+The current \texttt{benchmarks/output/summary.json} was generated on 2026-07-13T15:07:26.566Z with command \texttt{node benchmarks/run.js --provider mock --dimensions 64} (Ledger: E24). It reports:
 
 \begin{verbatim}
 | System | Score Percent | Pass Rate | Average Duration Ms |
-| Audrey | 100 | 100 | 16.583333333333332 |
-| Vector Only | 41.66666666666667 | 25 | 0.16666666666666666 |
-| Keyword + Recency | 41.66666666666667 | 25 | 0.75 |
-| Recent Window | 37.5 | 25 | 0 |
+| Audrey | 100 | 100 | 19.333333333333332 |
+| Vector Only | 41.66666666666667 | 25 | 0.25 |
+| Keyword + Recency | 41.66666666666667 | 25 | 0.5833333333333334 |
+| Recent Window | 37.5 | 25 | 0.08333333333333333 |
 \end{verbatim}
 
 This output is a regression-gate result. The baselines are toy local baselines used to catch retrieval and lifecycle regressions in the Audrey codebase. They are not external systems, not tuned competitor implementations, and not GuardBench baselines (Ledger: E23-E24). The current suite covers retrieval and operation families such as information extraction, knowledge updates, multi-session reasoning, conflict resolution, procedural learning, privacy boundary, overwrite, delete-and-abstain, semantic merge, and procedural merge (Ledger: E23-E24).
@@ -761,7 +761,7 @@ It reports local adapters only, not external-system comparisons (Ledger: E46):
 | Evidence recall | 100% |
 | Redaction leaks | 0 |
 | Recall-degradation detection | 100% |
-| Guard latency p50 / p95 | 4.253 ms / 21.196 ms |
+| Guard latency p50 / p95 | 4.607 ms / 21.585 ms |
 | Published artifact raw-secret leaks | 0 |
 | Audrey Guard decision accuracy | 100% |
 | No-memory decision accuracy | 10% |

package/docs/paper/output/arxiv-compile-report.json

@@ -1,13 +1,13 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "Audrey arXiv compile check",
-  "generatedAt": "2026-07-13T14:48:57.090Z",
+  "generatedAt": "2026-07-13T15:07:39.643Z",
   "source": {
     "sourceDir": "docs/paper/output/arxiv",
     "manifest": "docs/paper/output/arxiv/arxiv-manifest.json",
-    "manifestSha256": "de555f986f650735f8b4184eb93504b20d94dbd1e8510d839311fbf7e7d69429",
+    "manifestSha256": "d91eaefbca39c49e79990ef58314bbaa502184dae14596a498c2b6d8ba2f7df2",
     "mainTex": "docs/paper/output/arxiv/main.tex",
-    "mainTexSha256": "d9d0cf25cad4e59d6234643eb875bd5d74b4d45acd106e9bc01c7454e7240622",
+    "mainTexSha256": "0e122e6bd050e3fbf8e62ab3b363b12ebb00c7c8a4618b9fa4971d19e798bcc7",
     "referencesBib": "docs/paper/output/arxiv/references.bib",
     "referencesBibSha256": "c0bfcaf7bfe37d6933c812e46352be8a95397eaa430a0f5bc94037600a53f654"
   },

package/docs/paper/output/submission-bundle/README.md

@@ -390,7 +390,7 @@ npm run pack:check
 GuardBench currently contains ten local, deterministic pre-action scenarios covering repeated failures, procedures, scope changes, recovery, redaction, conflicting instructions, and noisy stores. The checked-in v1 methodology uses a mock 64-dimensional embedding provider and exists to catch regressions. A perfect local pass is not a claim about real-provider latency or production false-positive rates.
 
 <!-- guardbench-summary:start -->
-Latest local result in this checkout: 10/10 scenarios passed, 100% prevention rate, 0% false-block rate, 0 raw secret leaks, 0 published artifact leaks, and 4.253ms / 21.196ms p50/p95 Guard latency under the mock-provider methodology.
+Latest local result in this checkout: 10/10 scenarios passed, 100% prevention rate, 0% false-block rate, 0 raw secret leaks, 0 published artifact leaks, and 4.607ms / 21.585ms p50/p95 Guard latency under the mock-provider methodology.
 <!-- guardbench-summary:end -->
 
 `benchmarks/perf-snapshot.js` measures encode and hybrid-recall p50/p95/p99 at configurable corpus sizes with machine and provider provenance. Run it on the hardware and embedding provider you plan to operate; hosted-provider latency is dominated by its network round trip.

package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "GuardBench adapter self-test",
-  "generatedAt": "2026-07-13T14:48:54.144Z",
+  "generatedAt": "2026-07-13T15:07:36.556Z",
   "ok": true,
   "adapter": {
     "name": "Example Allow Adapter",
@@ -27,9 +27,9 @@
     "evidenceRecall": 0.1,
     "redactionLeaks": 0,
     "latency": {
-      "p50Ms": 0.011,
-      "p95Ms": 0.041,
-      "maxMs": 0.041
+      "p50Ms": 0.014,
+      "p95Ms": 0.045,
+      "maxMs": 0.045
     }
   },
   "contract": {

package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "GuardBench external adapter dry-run matrix",
-  "generatedAt": "2026-07-13T14:48:54.712Z",
+  "generatedAt": "2026-07-13T15:07:37.142Z",
   "ok": true,
   "registry": "benchmarks/adapters/registry.json",
   "outRoot": "benchmarks/output/external",

package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "GuardBench external evidence verification",
-  "generatedAt": "2026-07-13T14:48:54.992Z",
+  "generatedAt": "2026-07-13T15:07:37.432Z",
   "ok": true,
   "allowPending": true,
   "registry": "benchmarks/adapters/registry.json",

package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
   "suite": "GuardBench conformance card",
-  "generatedAt": "2026-07-13T14:48:49.667Z",
+  "generatedAt": "2026-07-13T15:07:31.567Z",
   "sourceDir": "benchmarks/output",
   "manifestVersion": "0.2.0",
   "suiteId": "guardbench-local-comparative",
@@ -25,9 +25,9 @@
     "evidenceRecall": 1,
     "redactionLeaks": 0,
     "latency": {
-      "p50Ms": 4.253,
-      "p95Ms": 21.196,
-      "maxMs": 21.196
+      "p50Ms": 4.607,
+      "p95Ms": 21.585,
+      "maxMs": 21.585
     }
   },
   "conformance": {
@@ -39,21 +39,21 @@
   "integrity": {
     "artifactHashes": {
       "guardbench-manifest.json": "57636ce19fdaa6e50fc3fc961d9e499a9f43632f588c713a9fefe8e8a6fa724c",
-      "guardbench-summary.json": "3ba1c059558aa8b511ae510276078930649ba6aca9669324148726fac10c7ee8",
-      "guardbench-raw.json": "786b03ff8570444620c23b35621bbb14897f06310de7e8bd3a337a1acf5ce776"
+      "guardbench-summary.json": "53b22e040ace0b91784e99684ffd740c95740171c00bf65388590aeb493c7c7d",
+      "guardbench-raw.json": "20a91ed7ca54a3b5b47b3a3f9ecde4ae8d53cc2b9bdbb5cb1ce6347e2224497b"
     },
     "externalRunMetadataHash": null
   },
   "provenance": {
-    "generatedAt": "2026-07-13T14:48:49.313Z",
-    "gitSha": "7111c630be69d3ab96439018f094dc4fac826aca",
+    "generatedAt": "2026-07-13T15:07:31.179Z",
+    "gitSha": "36842cfb0cad7ca5da864231a7e265229ba56fbd",
     "gitDirty": false,
     "node": "v24.18.0",
     "v8": "13.6.233.17-node.50",
     "platform": "linux",
     "arch": "x64",
     "osRelease": "6.17.0-1018-azure",
-    "cpuModel": "AMD EPYC 9V74 80-Core Processor",
+    "cpuModel": "AMD EPYC 7763 64-Core Processor",
     "cpuCount": 4,
     "totalMemoryGb": 15.61,
     "embeddingProvider": "mock",