From 172bbd74b0964beb31050701c69f1f20b06fd11b Mon Sep 17 00:00:00 2001
From: coding-dev-tools <coding-dev-tools@users.noreply.github.com>
Date: Mon, 2 Nov 2026 01:22:45 -0500
Subject: [PATCH 1/4] chore(release): prepare 1.7.12 candidate

- Bump package, plugin, and commercial-manifest versions to 1.7.12
- Record the 1.7.12 changelog entry for automatic browser access, the salvaged
  verification tooling, and dependency/CI upkeep
- Refresh Claude plugin asset checksums

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
---
 .claude-plugin/marketplace.json    | 2 +-
 .claude-plugin/plugin.json         | 2 +-
 .claude-plugin/skill-assets.sha256 | 4 ++--
 CHANGELOG.md                       | 6 ++++++
 engraphis/__init__.py              | 4 ++--
 engraphis/commercial_manifest.json | 2 +-
 pyproject.toml                     | 2 +-
 7 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 3a5cbc7c..28bd40ba 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -9,7 +9,7 @@
       "name": "engraphis-memory",
       "source": "./",
       "description": "Discipline for giving agents durable, scoped, explainable memory across sessions and repos with the Engraphis MCP tools.",
-      "version": "1.7.11"
+      "version": "1.7.12"
     }
   ]
 }
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index 04678fd0..6e59e596 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
 {
   "name": "engraphis-memory",
-  "version": "1.7.11",
+  "version": "1.7.12",
   "description": "Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.",
   "author": {
     "name": "The Engraphis Authors",
diff --git a/.claude-plugin/skill-assets.sha256 b/.claude-plugin/skill-assets.sha256
index 29fcaf00..d23afae5 100644
--- a/.claude-plugin/skill-assets.sha256
+++ b/.claude-plugin/skill-assets.sha256
@@ -1,5 +1,5 @@
-cdace18081202f9bfb6e02c4098296e141a4071771073c79bf8e738e29008ca9  .claude-plugin/marketplace.json
-a2d659f33f62ee775174cb75a81fb740e66ed75ada23981968cae117196f3b24  .claude-plugin/plugin.json
+f6343d92f4c7249ea5789facf391c754537df888f0ca83373acad147e7a41c83  .claude-plugin/marketplace.json
+bb219dc0cec6364a6c29f3f5fdd4d4aee191840404a61e015a35d63b25d42b38  .claude-plugin/plugin.json
 aeee7a94671ceb306fe2d24c5acc9f2d96ad8a8e7410536566799eea6265f080  skills/engraphis-memory/SKILL.md
 055655db84af07561d002f0c69744313d8413c39f3e873f941f0fa0b1e76dc66  skills/engraphis-memory/references/CONVENTIONS.md
 9d090a03f5b3f36a34d91f66b72c3844591f6915755ac3a6c6ba5f1b16977de5  skills/engraphis-memory/references/SCOPING.md
diff --git a/CHANGELOG.md b/CHANGELOG.md
index fdac2dd3..2a515a32 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,10 @@ All notable changes to Engraphis are documented here. Format loosely follows
 
 ## [Unreleased]
 
+## [1.7.12] - 2026-11-02
+
+Candidate package version: **1.7.12**. Publication and hosted-service qualification remain separate.
+
 - Browsers no longer enter a token. The dashboard opens automatically for any browser that
   can reach it; the deployment's network reachability is the dashboard boundary. Session
   issuance still requires the same-origin custom header and a published Host, and only an
@@ -13,6 +17,8 @@ All notable changes to Engraphis are documented here. Format loosely follows
   `ENGRAPHIS_BROWSER_AUTO_SESSION=0` for a hardened deployment, where
   `engraphis-dashboard --link` (or `POST /api/auth/link`) issues a single-use, 15-minute
   sign-in link that opens a 12-hour browser session.
+- Add a Windows RAM integrity probe, a local pre-flight verification harness, and MCP memory concurrency test coverage.
+- Refresh evaluation, CI, and development dependencies and update the registered benchmark evidence registry.
 
 ## [1.7.11] - 2026-10-26
 
diff --git a/engraphis/__init__.py b/engraphis/__init__.py
index 0af1320c..9355bad1 100644
--- a/engraphis/__init__.py
+++ b/engraphis/__init__.py
@@ -2,7 +2,7 @@
 
 from importlib.metadata import PackageNotFoundError, version as _dist_version
 
-_SOURCE_VERSION = "1.7.11"
+_SOURCE_VERSION = "1.7.12"
 
 try:
     __version__ = _dist_version("engraphis")
@@ -14,7 +14,7 @@
 except PackageNotFoundError:  # source tree without an installed distribution
     # Keep in step with [project] version in pyproject.toml — tests/test_packaging.py
     # pins the two together so a release cannot ship them out of sync.
-    __version__ = "1.7.11"
+    __version__ = "1.7.12"
 
 
 def _default_memory_engine_factory(**kwargs):
diff --git a/engraphis/commercial_manifest.json b/engraphis/commercial_manifest.json
index a878931e..00cf1c72 100644
--- a/engraphis/commercial_manifest.json
+++ b/engraphis/commercial_manifest.json
@@ -1,6 +1,6 @@
 {
   "schema": "engraphis-commercial/v2",
-  "version": "1.7.11",
+  "version": "1.7.12",
   "control_plane": "https://api.engraphis.com",
   "account_portal": "https://api.engraphis.com/account",
   "billing": {
diff --git a/pyproject.toml b/pyproject.toml
index 97e8addd..e23dd269 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,7 +10,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "engraphis"
-version = "1.7.11"
+version = "1.7.12"
 description = "Local-first AI memory engine for agents — Ebbinghaus decay, interaction-aware recall, bi-temporal facts, hybrid retrieval, and an MCP server. You bring the LLM."
 readme = "README.md"
 license = "Apache-2.0"

From f29eff3cef9829b0af067290939af5c1b125b400 Mon Sep 17 00:00:00 2001
From: coding-dev-tools <coding-dev-tools@users.noreply.github.com>
Date: Mon, 2 Nov 2026 00:10:34 -0500
Subject: [PATCH 2/4] docs(readme): state Jev is free for Pro and Team up front

- Lead the Jev section with "included free with every paid plan: Pro and Team"
- Keep the entitlement, rolling limits, fleet guard, consent, and BYOK terms intact
- Record the clarification under Unreleased

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
---
 CHANGELOG.md |  2 ++
 README.md    | 23 +++++------------------
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2a515a32..6caad0d3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -18,6 +18,8 @@ Candidate package version: **1.7.12**. Publication and hosted-service qualificat
   `engraphis-dashboard --link` (or `POST /api/auth/link`) issues a single-use, 15-minute
   sign-in link that opens a 12-hour browser session.
 - Add a Windows RAM integrity probe, a local pre-flight verification harness, and MCP memory concurrency test coverage.
+- State plainly in the README that Jev is included free with every paid plan (Pro and Team),
+  with the existing rolling limits and per-call consent rules unchanged.
 - Refresh evaluation, CI, and development dependencies and update the registered benchmark evidence registry.
 
 ## [1.7.11] - 2026-10-26
diff --git a/README.md b/README.md
index 0ae6e6bd..ff315afe 100644
--- a/README.md
+++ b/README.md
@@ -66,29 +66,16 @@ The payload figure is a serialized JSON-shape estimate, not an MCP transport mea
 
 ## Optional Jev assistance
 
-Use **Review with Jev** in the local dashboard to check whether selected evidence can answer a question or compare two memories for a possible contradiction. Remote review sends only selected, bounded excerpts and the supplied question after per-call consent and `public` or `internal` classification. Secret, malformed, and unknown sensitivity classifications are blocked. The existing MCP decision tool handles command and completion reviews.
+**Jev is included free with every paid plan: Pro and Team.** After enablement, every legitimate Pro user and each eligible Team named seat, including paid viewers, with an active paid, trial, or test entitlement receives managed Jev at no additional customer charge and without a personal provider key. Local advisory decisions stay free for everyone; BYOK, a personal TypeSafe key, is optional for non-paid or direct use and its provider charges may apply. Managed Jev is currently `not_yet_available` pending release acceptance and service-capacity qualification; client configuration does not enable it.
 
-Recall route selection is experimental and BYOK-only. Smart MCP opts in through `engraphis_recall_context` with `allow_remote=true` and a `public` or `internal` classification. Classic MCP also requires `planning="auto"` and `jev_assisted=true`. Jev receives the original query and bounded deterministic routes, not recalled memory bodies; it cannot change scope, time, type, or trust filters. Local behavior is the default. Uncertain, malformed, or failed requests fall back to deterministic behavior. Jev cannot write memories, change grounded-recall requirements, authorize commands, or certify completion. Direct BYOK use may incur provider charges.
+Each individual receives all three independent rolling limits: **100 evaluated questions per rolling hour, 1,000 per rolling five hours, and 2,000 per rolling 24 hours**. Usage is per person, not pooled across a Team and not monthly. Each evaluated question counts once; if a batch is evaluated, every question counts. Admitted attempts that fail or are interrupted remain counted. No overage is charged.
 
-Jev-assisted recall planning is experimental. In an exploratory comparison using 40 public synthetic tasks, Jev selected a route on all 40 calls but did not change nDCG@5, Recall@5, or answer-token coverage. This fixture does not establish a benefit on held-out user workloads, so no retrieval-quality improvement is claimed.
+The existing production fleet guard remains 100 questions per day across the service. That limit conflicts with these per-person rolling caps and may pause or reject requests earlier, so resolve capacity and the fleet guard before launch.
 
-Managed Jev is currently `not_yet_available` pending release acceptance and
-service-capacity qualification; client configuration does not enable it. After
-enablement, every legitimate Pro user and each eligible Team named seat, including paid
-viewers, with an active paid, trial, or test entitlement receives managed Jev at no
-additional customer charge and without a personal provider key.
+Use **Review with Jev** in the local dashboard for evidence-support and contradiction checks; the MCP decision tool covers command and completion reviews. Remote calls need per-call consent plus a `public` or `internal` classification, and Jev cannot write memories, change grounded-recall requirements, authorize commands, or certify completion.
 
-Each individual receives all three independent rolling limits: **100 evaluated questions per rolling hour, 1,000 per rolling five hours, and 2,000 per rolling 24 hours**. Usage is per
-person, not pooled across a Team and not monthly. Each evaluated question counts once;
-if a batch is evaluated, every question counts, and command review evaluates two
-questions. Admitted attempts that fail or are interrupted remain counted. No overage is
-charged. The account portal reports each member's remaining usage across all three
-windows; usage returns as earlier questions leave each rolling window.
+Recall route selection is experimental and BYOK-only: `engraphis_recall_context` with `allow_remote=true`, or classic MCP with `planning="auto"` and `jev_assisted=true`. On 40 public synthetic tasks it changed no retrieval quality, so no retrieval-quality improvement is claimed.
 
-The existing production fleet guard remains 100 questions per day across the service.
-That limit conflicts with these per-person rolling caps and may pause or reject requests
-earlier. Resolve capacity and the fleet guard before launch. The supported decisions are
-advisory; current synthetic fixtures do not demonstrate Jev accuracy or cost savings.
 See [hosted plans and Jev details](https://github.com/Coding-Dev-Tools/engraphis/blob/522def372c45a26d46bc7a05829964ae0240f3a9/docs/HOSTED_PLANS.md#included-system-1-decision-engine-jev).
 
 ## Guides

From ee27261cce816f147fe278396f7cfd83ed8a0779 Mon Sep 17 00:00:00 2001
From: coding-dev-tools <coding-dev-tools@users.noreply.github.com>
Date: Mon, 2 Nov 2026 18:22:02 -0500
Subject: [PATCH 3/4] fix(sync,manifest): record sync authorization denial and
 support public-offer cloud contract

- Record authoritative entitlement denial when POST /api/sync/run fails with 401/402/403, and return account_url() when connected to prevent lapsed Team users from misrouting to Pro checkout
- Accept schema 'engraphis-public-offer/v1' in scripts/check_commercial_manifest.py --cloud-contract to cleanly validate against engraphis-cloud
- Add regression test in tests/test_sync_dashboard.py

Agent: antigravity
---
 engraphis/routes/v2_api.py           |  4 +++-
 scripts/check_commercial_manifest.py |  6 +++++-
 tests/test_sync_dashboard.py         | 22 ++++++++++++++++++++++
 3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/engraphis/routes/v2_api.py b/engraphis/routes/v2_api.py
index 23771993..3ec59f65 100644
--- a/engraphis/routes/v2_api.py
+++ b/engraphis/routes/v2_api.py
@@ -4580,8 +4580,10 @@ async def sync_run():
         and len(authorization_errors) == len(summary["errors"])
     ):
         first = authorization_errors[0]
+        _record_authoritative_denial()
+        recovery_url = licensing.account_url() if has_cloud_session else licensing.upgrade_url()
         raise HTTPException(status_code=first["status"], detail={
-            "error": first["error"], "upgrade_url": licensing.upgrade_url()})
+            "error": first["error"], "upgrade_url": recovery_url})
     return {"ok": not summary["errors"], "summary": summary}
 
 
diff --git a/scripts/check_commercial_manifest.py b/scripts/check_commercial_manifest.py
index 0aa95e31..923cd8ab 100644
--- a/scripts/check_commercial_manifest.py
+++ b/scripts/check_commercial_manifest.py
@@ -235,7 +235,11 @@ def main() -> int:
     _check_repository(manifest, errors)
     if args.cloud_contract:
         cloud = json.loads(args.cloud_contract.read_text(encoding="utf-8-sig"))
-        if cloud.get("schema_version") != 1 or cloud.get("trial", {}).get("days_by_plan") != manifest["trial"]["days_by_plan"]:
+        schema_valid = (
+            cloud.get("schema_version") == 1
+            or cloud.get("schema") == "engraphis-public-offer/v1"
+        )
+        if not schema_valid or cloud.get("trial", {}).get("days_by_plan") != manifest["trial"]["days_by_plan"]:
             _fail(errors, "cloud trial authority differs from the public per-plan contract")
     if args.website_root:
         _check_website(manifest, args.website_root.resolve(), errors)
diff --git a/tests/test_sync_dashboard.py b/tests/test_sync_dashboard.py
index 98f16185..cd9b0a23 100644
--- a/tests/test_sync_dashboard.py
+++ b/tests/test_sync_dashboard.py
@@ -412,3 +412,25 @@ def fail_session(*args, **kwargs):
         "status": 503,
     }]
     assert "private network detail" not in repr(summary)
+
+
+def test_sync_run_total_authorization_loss_records_denial_and_routes_to_account_url(
+    monkeypatch, tmp_path
+):
+    from engraphis import licensing
+    from engraphis.cloud_session import CloudSessionError
+    from engraphis.routes import v2_api
+
+    denials = []
+    monkeypatch.setattr(v2_api, "_record_authoritative_denial", lambda: denials.append(True))
+
+    def fail_access(*args, **kwargs):
+        raise CloudSessionError("subscription lapsed", status=402)
+
+    monkeypatch.setattr("engraphis.cloud_session.access_for_workspace", fail_access)
+    with _client(monkeypatch, tmp_path, cloud=True) as c:
+        response = c.post("/api/sync/run", json={})
+
+    assert response.status_code == 402
+    assert response.json()["detail"]["upgrade_url"] == licensing.account_url()
+    assert denials == [True]

From aa3f6bac06f6a734e8f409d9973ab05e3702c650 Mon Sep 17 00:00:00 2001
From: coding-dev-tools <coding-dev-tools@users.noreply.github.com>
Date: Tue, 3 Nov 2026 00:24:15 -0500
Subject: [PATCH 4/4] fix(benchmark,eval): isolate offline chunking eval and
 refresh 1.7.12 release evidence

- Ensure chunking_eval uses retention_supervisor=none so offline evaluations
  remain deterministic and independent of local user LLM retention settings
- Export fresh immutable offline evidence artifact for 1.7.12 release
- Update benchmark report images (SVG and PNG provenance chunks)
- Bind new fixture digest and artifact sha256 across tests and documentation

Agent: antigravity
---
 BENCHMARKS.md                                 |  12 +-
 README.md                                     |   2 +-
 ...line-fixtures-release-1.7.12-20261102.json | 701 ++++++++++++++++++
 ...xtures-release-1.7.12-20261102.json.sha256 |   1 +
 docs/images/context-efficiency.png            | Bin 61488 -> 61488 bytes
 docs/images/context-efficiency.svg            |   4 +-
 .../images/evidence-backed-agent-examples.png | Bin 273392 -> 273392 bytes
 .../images/evidence-backed-agent-examples.svg |   4 +-
 eval/chunking_eval.py                         |   3 +-
 tests/test_benchmark_evidence.py              |   4 +-
 10 files changed, 717 insertions(+), 14 deletions(-)
 create mode 100644 docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json
 create mode 100644 docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json.sha256

diff --git a/BENCHMARKS.md b/BENCHMARKS.md
index 60981083..6cb1a2c7 100644
--- a/BENCHMARKS.md
+++ b/BENCHMARKS.md
@@ -94,14 +94,14 @@ interpretation and do not count as additional benchmark-quality gains.
 ### Public numeric evidence registry
 
 Every exact public aggregate retained below comes from the checked-in, public-safe
-[`offline-fixtures-automatic-browser-access-20261101.json`](docs/benchmark-evidence/offline-fixtures-automatic-browser-access-20261101.json) artifact. Its
+[`offline-fixtures-release-1.7.12-20261102.json`](docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json) artifact. Its
 SHA-256 is
-`8df20fd0a97f20070ac26628e19b5ae1be653cd7aa9c7399d424cedf0e839a01`, also recorded in the
+`025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660`, also recorded in the
 adjacent `.sha256` file. The artifact contains no raw questions, answers, prompts, customer data,
 or per-record content fingerprints.
 
 The fixture-suite digest is
-`0179ada4cfffd827e2d1cf2cce1b5110862ac9a5cafbbf0db6dcd6e975e864ce`. The artifact defines
+`54422b65475bb0d3e5c4ad0613bbda87dd5e01cb43e15513469b7306446831c9`. The artifact defines
 the digest algorithm and records the SHA-256 of every suite and dataset file. Each evidence ID
 also binds its exact command through `sha256(UTF-8 exact command)`:
 
@@ -134,7 +134,7 @@ retrieval-quality improvement. It does not qualify browser behavior, hosted serv
 external models, or provider billing. The registered artifact was produced with:
 
 ```bash
-python -m scripts.export_offline_evidence --output docs/benchmark-evidence/offline-fixtures-automatic-browser-access-20261101.json
+python -m scripts.export_offline_evidence --output docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json
 ```
 
 The earlier release-review predecessors,
@@ -203,13 +203,13 @@ grounded checks in separate panels; provider billing and MCP transport are not m
 the SVG and matching PNG with:
 
 ```bash
-python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-automatic-browser-access-20261101.json --output docs/images/context-efficiency.svg --png-output docs/images/context-efficiency.png
+python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json --output docs/images/context-efficiency.svg --png-output docs/images/context-efficiency.png
 ```
 
 The companion examples are also generated from that artifact with:
 
 ```bash
-python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-automatic-browser-access-20261101.json --output docs/images/evidence-backed-agent-examples.svg --png-output docs/images/evidence-backed-agent-examples.png
+python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json --output docs/images/evidence-backed-agent-examples.svg --png-output docs/images/evidence-backed-agent-examples.png
 ```
 The historical-to-executable mapping is in
 [`docs/BENCHMARK_CHANGE_COVERAGE.md`](docs/BENCHMARK_CHANGE_COVERAGE.md).
diff --git a/README.md b/README.md
index ff315afe..0f02aacf 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,7 @@ Connect a coding agent over MCP with the [agent setup guide](https://github.com/
 The current registered artifact contains three deterministic offline fixture runs. It separates context size, retrieval quality, and grounded decision checks; these small fixtures do not establish general task performance.
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Coding-Dev-Tools/engraphis/99af3855bd6b685cbac4a4489b44b3c374129053/docs/images/context-efficiency.svg" alt="Three registered offline fixtures: structure-aware chunking reduced mean retrieved context from 740.3 to 214.3 tokens per question (71.1%, 18 questions); the serialized JSON-shape proxy fell from 24,590 to 11,138 tokens across 26 payload samples and 260 recalls. Candidate and packed retrieval quality (Recall@5, Hit@5, and answer-token recall) are shown separately (each 1.000). Grounded checks show 5/5 answerable queries grounded and 6/6 abstention queries rejected, including a 1/1 quarantined-evidence probe; 11/11 decisions were correct. MCP transport and provider billing were not measured. Artifact SHA-256 prefix 8df20fd0a97f; see the benchmark guide for the full checksum." width="100%">
+  <img src="https://raw.githubusercontent.com/Coding-Dev-Tools/engraphis/99af3855bd6b685cbac4a4489b44b3c374129053/docs/images/context-efficiency.svg" alt="Three registered offline fixtures: structure-aware chunking reduced mean retrieved context from 740.3 to 214.3 tokens per question (71.1%, 18 questions); the serialized JSON-shape proxy fell from 24,590 to 11,138 tokens across 26 payload samples and 260 recalls. Candidate and packed retrieval quality (Recall@5, Hit@5, and answer-token recall) are shown separately (each 1.000). Grounded checks show 5/5 answerable queries grounded and 6/6 abstention queries rejected, including a 1/1 quarantined-evidence probe; 11/11 decisions were correct. MCP transport and provider billing were not measured. Artifact SHA-256 prefix 025183601c5a; see the benchmark guide for the full checksum." width="100%">
   <br>
   <sup>Three offline fixtures separate context reduction, candidate and packed retrieval quality, and grounded behavior. The chart shows the artifact checksum prefix; see the benchmark guide for the full checksum and reproduction steps.</sup>
 </p>
diff --git a/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json b/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json
new file mode 100644
index 00000000..1395df19
--- /dev/null
+++ b/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json
@@ -0,0 +1,701 @@
+{
+  "environment": {
+    "embedding": "deterministic",
+    "numpy": "2.4.6",
+    "platform": "win32",
+    "python": "3.11.17",
+    "vector_backend": "numpy"
+  },
+  "generated_on": "2026-11-03",
+  "privacy": {
+    "contains_answers": false,
+    "contains_customer_data": false,
+    "contains_per_record_fingerprints": false,
+    "contains_prompts": false,
+    "contains_raw_questions": false
+  },
+  "runs": [
+    {
+      "boundary": "Deterministic offline retrieval fixture; normalized-character token estimator; not external QA or provider billing.",
+      "command": "python -m eval.chunking_eval --dataset eval/datasets/longdoc.jsonl --k 5",
+      "config_digest": "c1c8196aa7e1568ef3844a9fb2d76b87f342c39108e32d6ad144b885a76143b8",
+      "config_digest_method": "sha256(UTF-8 exact command)",
+      "id": "offline-chunking",
+      "result": {
+        "chunked": {
+          "max_stored_tokens": 59,
+          "mean_context_tokens": 214.3,
+          "mean_evidence_tokens": 42.4,
+          "memories": 24,
+          "recall_at_k": 1.0
+        },
+        "context_reduction_pct": 71.1,
+        "documents": 6,
+        "k": 5,
+        "questions": 18,
+        "token_counter": "engraphis.chars4.v1",
+        "whole": {
+          "max_stored_tokens": 213,
+          "mean_context_tokens": 740.3,
+          "mean_evidence_tokens": 162.2,
+          "memories": 6,
+          "recall_at_k": 1.0
+        }
+      }
+    },
+    {
+      "boundary": "Deterministic offline CodeMem fixture; serialized JSON-shape payload proxies, not MCP transport responses, provider billing, or latency claims.",
+      "command": "python -m eval.performance --dataset eval/datasets/codemem.jsonl --k 5 --iterations 10 --json",
+      "config_digest": "bbe4aca81e58d4830e50a8fc7729a1d15b71d97a6299bccd79432b7f119677d7",
+      "config_digest_method": "sha256(UTF-8 exact command)",
+      "id": "offline-performance",
+      "result": {
+        "answer_token_recall": 1.0,
+        "compact_serialized_payload_tokens": 11138,
+        "dataset_cases": 14,
+        "full_serialized_payload_tokens": 24590,
+        "hit_at_k": 1.0,
+        "k": 5,
+        "max_context_tokens": 108,
+        "mean_context_tokens": 85.38,
+        "memories": 44,
+        "packed_quality": {
+          "answer_token_recall": 1.0,
+          "hit_at_k": 1.0,
+          "recall_at_k": 1.0,
+          "sample_count": 26
+        },
+        "payload_boundary": {
+          "kind": "serialized_json_shape_proxy",
+          "mcp_envelope_serialized": false,
+          "token_counter": "engraphis.regex.v1",
+          "transport_measured": false
+        },
+        "quality_scope": {
+          "packed": "packed_quality fields score only chunks admitted to reader context",
+          "retrieved": "legacy quality fields score all candidate chunks returned before context packing"
+        },
+        "questions": 26,
+        "recall_at_k": 1.0,
+        "saved_serialized_payload_tokens": 13452,
+        "serialized_payload_savings_ratio": 0.5471,
+        "timed_recalls": 260,
+        "token_budget": 1500,
+        "token_counter": "engraphis.regex.v1"
+      }
+    },
+    {
+      "boundary": "Deterministic offline support/abstention fixture; not a frontier-model answer-quality score.",
+      "command": "python -m eval.grounded",
+      "config_digest": "590442e51e3642c10489165759919dc86ffac62c182937330c153e7f8d5fc26f",
+      "config_digest_method": "sha256(UTF-8 exact command)",
+      "id": "offline-grounded",
+      "result": {
+        "abstained": 6,
+        "answerable": 5,
+        "decision_accuracy": 1.0,
+        "grounded": 5,
+        "off_topic": 6,
+        "quarantine_hits": 1,
+        "quarantined": 1
+      }
+    }
+  ],
+  "schema": "engraphis-public-offline-fixtures/v1",
+  "suite": {
+    "digest": "54422b65475bb0d3e5c4ad0613bbda87dd5e01cb43e15513469b7306446831c9",
+    "digest_method": "sha256(canonical compact JSON mapping each sorted path to its file SHA-256)",
+    "files": {
+      "engraphis/__init__.py": "1cde9f19e05ddc4f5f28517e00b0a7bd5ebf09d6be8ec2681cebf5b698195d70",
+      "engraphis/ai_context.py": "4dfd5d39eb95d05c591d1981e9e855eced73232f53efd9fe9966e0e08957d030",
+      "engraphis/app.py": "44d68ad8c0ff46baed01978c9b04e40b8be5031609d5a69e205b7f05da3777fb",
+      "engraphis/backends/__init__.py": "a9f22b9278362904166614081f1df78469d453601b298ce4e8afdba8a3722b25",
+      "engraphis/backends/codegraph.py": "83e723a91068d23694092fbe00157fcb2597061d453eb36f955bf55bc5b4d35e",
+      "engraphis/backends/embedder_api.py": "56a6bceea4f757325dcea987b0339e41d3875634b1ae5103f0537a358cf5878b",
+      "engraphis/backends/embedder_deterministic.py": "ee2476c33ba83a9bba5d7caaa4dbb40861ee22cbdb1cf3c1092ca6c018a6c38f",
+      "engraphis/backends/embedder_st.py": "c497b47038227516a0bc43d4bc0a91fc46d267bbffb0382c0b893e44f016d6b4",
+      "engraphis/backends/encrypted_db.py": "25f6c1480d296a88f317213700a8b3c81e2732399bfac464b0d893465b25e846",
+      "engraphis/backends/extractor.py": "f2e3455ab7f14caee1d5b5c4ef071e498e90118f1b0ddcb8510c969583b0fc57",
+      "engraphis/backends/graph_extractor.py": "88561efa0d3fabc447a0a005b10e36261379d46218cf62d905e6928cd2fda676",
+      "engraphis/backends/jev_decision.py": "31d4a789a013226f5be3eb47c54d3ca34af09b1c77b7c9ab1f57622035951d08",
+      "engraphis/backends/jev_query_planner.py": "c64818474c15acf5d42f673f8084f0fbf782e78b23b1f8cb9a32d6d044d5af63",
+      "engraphis/backends/jev_transport.py": "e65368169d53998d3e02cc78a42ed7c92fd27749cc1c9b4f95aa856e618a0ee9",
+      "engraphis/backends/model_source.py": "8c3c7681f95214a2bbabd8de222e5ee11f42fe13402d27365654ae75fb363d4e",
+      "engraphis/backends/postgres_schema.py": "8468578c3add701d30d5eaa36d768ded2375d116e55f1836e09f6107a07a267e",
+      "engraphis/backends/query_planner.py": "bbdd77afc9b5523421b85b2ae63c8da7f5a7b777265450e0d21708a83e7bb23c",
+      "engraphis/backends/reranker.py": "747761d6cbfa421388974bcfd98d844f92391d80f4bf6a4feca00b0c7a6908ca",
+      "engraphis/backends/resources.py": "47cc867c3aecc8bd95fa284bc5bb04715f3339c19a0a11512973ef6171c95944",
+      "engraphis/backends/retention.py": "381d9371e3951d762f8b55eb54711de5697642acb39de99a714f246c059ecbd0",
+      "engraphis/backends/sync_folder.py": "e4f70a92a17f6a365910670df041e6e3ca421d44ada2827917cd66b4dc067bfa",
+      "engraphis/backends/sync_relay.py": "b8b9ad265453aba17ba7c27a355e12a793469b3e44cb217943c6fad9382a3006",
+      "engraphis/backends/vector_numpy.py": "c598831bea547824cfe08844816fa79857d3617cb0631238f95dad955a424f72",
+      "engraphis/backends/vector_sqlitevec.py": "6148e14ceaacc19239b64c642a3fba0e98797c78cec356210157afadf475a08b",
+      "engraphis/build_info.py": "624c22471e56d4c4047160808c4245488292af611564d1a63ca437605bbb414f",
+      "engraphis/cloud_authz.py": "e80500579cb3a1d5fbf30814dc94e3e3967e50b311e8ed2fa56afcc13f7eb565",
+      "engraphis/cloud_features.py": "90e876f8993d99f01760cd01ae9fb63140e3f65036706e8fb0c8224560416330",
+      "engraphis/cloud_session.py": "cc6ab27c6af69b5c676e721ab06c520730e205f5bbffe27818650edfb71d4b63",
+      "engraphis/commercial.py": "184f312066a9e682e51a0abeff042f1c0e8eed2d47470157b23930b5a17633aa",
+      "engraphis/config.py": "7a1aa04246bda341f26866c5145854412e8c157d9880212fe1d7579ac986b764",
+      "engraphis/core/__init__.py": "dd5143729c3939237f04636f437032b1f2d3a5f7d82c91bbc2a5a283c3f0ebaa",
+      "engraphis/core/adaptive_context.py": "cc5ce48109bb0d5230a5b2b8424b829c853feec5b5d5b82596413f2279b0c9f9",
+      "engraphis/core/browsing.py": "cfae752d52ef51b17c4ffbe44dde62d5b0e1ed0ca34ec0e1788f3991d94bf05f",
+      "engraphis/core/codegraph_export.py": "4641074258d7b23498f92dd45053a0fbb111863eaad2001c08e5e3c2dc2fd54f",
+      "engraphis/core/conflicts.py": "28530be25a4af0bffd8f609b965b33ca7f93199a70887789b2148fda8a61a486",
+      "engraphis/core/consolidate.py": "f66eedfe08319a64b761261ccf1c99b163eba564d6d4060534bf8c575aecf232",
+      "engraphis/core/context.py": "8cc15746e4de88bce7d34db8c11dfaa545f17305788e2167a286179171717fb9",
+      "engraphis/core/diagnostics.py": "5ba449bdf5087d8ccb5808379596e695c8f405da497372e99f2bac509f96e8e4",
+      "engraphis/core/documents.py": "9b4a5dce557bbd25217c61b51d5838a8b7c693c77f7a700d010ed607cb39b150",
+      "engraphis/core/engine.py": "c908dea96113a97dcd56679f62c9e587b28130204888b16e4c8e64d68f47d3fe",
+      "engraphis/core/evidence.py": "97912b52a3d22de909218f83c09c92572ed695d7b3c2117e5330271c6d84a7bd",
+      "engraphis/core/fsutil.py": "6db770fa8bd3e1a57dfa70eb8e8bc46d48c2dc53ead1b0b43eeecf085ef58cfc",
+      "engraphis/core/graph_layers.py": "64d74ab01c77119f6343ba6f1d6a84f9653f1a5d34d47ce7966f3ac31b29d2ea",
+      "engraphis/core/graph_policy.py": "ec5b373d01adb2de87df31d9f543130018e9a73faaaed239a184f14a32646615",
+      "engraphis/core/graph_scene.py": "b79c53e156b11102d64196ac5082c6549c13fe0cc57b9760d66872459a0f2110",
+      "engraphis/core/graphrank.py": "1279a58396104d3f906bfd5ec75b32efedfefe52201467bf19d80be3517017a5",
+      "engraphis/core/grounded.py": "0d6b60ef16f3cd65b7032bdb60ba853dac364d0df58a74c932ecf12aec98e4b7",
+      "engraphis/core/ids.py": "e47eeadfaf560bc7638e1879fc491fa82d981cd42b9e4b05ef87033b2d7dfa60",
+      "engraphis/core/interfaces.py": "bd5f7f4751a035348cf99cae3e8be64f205cb2cb8fb6eb3bd7e56f5099d81f0f",
+      "engraphis/core/mutations.py": "3d32b63f530204ae0394f3ebafbdf667cd86143a863ca808527d1e754d3a246e",
+      "engraphis/core/obsidian.py": "39fa18707972563581b06fa129e03841200b8bc05a114876cbbb7f352a885bee",
+      "engraphis/core/poisoning.py": "e91b6b23d2717680b3f25a7a540ba04e19e815e4ce4744bdb70da9bada21e031",
+      "engraphis/core/query_planner.py": "249062d67392ab7c203cc71e9040e99bee91bf570604e90949149a93cb652120",
+      "engraphis/core/read_snapshots.py": "be08e63a88bd38ed91d61b28657a65201c38994856db2798b209a73151dd202a",
+      "engraphis/core/recall.py": "b56dc6736414cab451bb195df7948a6088c7ae5e14f5961d57daffb4a5bafb28",
+      "engraphis/core/relocation.py": "86bbd292b374539b480dddc1a9ac19292fbc17ff9fa8e1fe6ff69c91ee7c8bb9",
+      "engraphis/core/resolve.py": "f01a6f55e44320ab04b97e516342f20155668863b2fc4765305e066d87586524",
+      "engraphis/core/retention_policy.py": "864c03bdb6e743cd0002c706de471e920f1fa1f1a9918ab343ef4c2042b47429",
+      "engraphis/core/retrieval_policy.py": "d169eb442115bd06c1e1da776fa6c1849e0795e658edd732a8d6821326b46b03",
+      "engraphis/core/savings.py": "e34a8f4a26c313a1e439dada16b7fd4a0c3fada2038e2f4aed03978b53310bbc",
+      "engraphis/core/schema.py": "8384672f2d5406abc5969a3e134e14684d71dbeb44685f8198023b8e3f03be77",
+      "engraphis/core/scoring.py": "bf0cf02521ab3dae6de4a0e7c9892bf3feb02f73de22478c7fb0c64ce55ab0d3",
+      "engraphis/core/secrets.py": "78ab40870d6c5918c189307028b107df239d08cd918abe08c85fa15b58fa1663",
+      "engraphis/core/source_paths.py": "2e71de7f19f260b335137602f07a28a80efa5d65e3d2497215356ba5f172b47e",
+      "engraphis/core/spec_crawl.py": "23359f9e28a2a68a3abe59f1e705b8be1f6c72880d708123bc85391029e769e5",
+      "engraphis/core/store.py": "b04fc2cfc162539e54d80691f84dda4b4f454f2be1d31027776d5e49655fe8e8",
+      "engraphis/core/sync.py": "0d28dd697eb8e8acdb7fed3e346fcba8fce23cbf4606eb11de68cb1fb001fcf2",
+      "engraphis/core/textutil.py": "acd65031729fa5d91d09527b8eb52518b83cfce77a55e6b7ae2d94686e35c1a6",
+      "engraphis/core/user_model.py": "3147ec8ee7cfd855783f639874b63f331cdc822bd8bd9298cfb326dd18666026",
+      "engraphis/core/vector_repair.py": "a8c1812de4e3ed288eda3e54a505e136d6ebd3ec296788bcbb8804b11e13cfc8",
+      "engraphis/core/vector_search.py": "75800052e573e9af01c6fd098eaf8647c3c45cd7eb2601dae05d42359e19b234",
+      "engraphis/dashboard_app.py": "77546609aa29031dbf935228ee00162b3635f4c3438d2a5922bfe94eb211a084",
+      "engraphis/dashboard_assets/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+      "engraphis/device_connect.py": "c8cd0a22e9fd2d92a65bd74047cc3a8b7159bfc9a297cb639c1c7f1699f8802e",
+      "engraphis/document_import.py": "5378d17355cbf97db304ea8ac2d1978206b244b553c7e0645f8a060d272664b5",
+      "engraphis/engines/__init__.py": "111232af583889195c5f5a60298e32484348608e81d2bdd822fd3ecd2a33c1e4",
+      "engraphis/engines/embedder.py": "998b65dd566966bb6581fd9f09cdf46c58a3923ef5df3073ccdaa541153a3581",
+      "engraphis/engines/ingest.py": "1a5d4b52c13e533864329f9fff11c0f6ebc299ff7093a9d9275e5c9626a39ce2",
+      "engraphis/engines/intelligence.py": "b561589b98deb98271f104dfec6276aeba13c4815e627259be5f8769f2e7ad82",
+      "engraphis/engines/recall.py": "f979580d065599c07acbc3add59f71e52d9a186a2104b0e257daa7959ea88d26",
+      "engraphis/engines/reweight.py": "91ec5815f5d356a7068c36133d24405334450f361f902f99275bed3ccebffd49",
+      "engraphis/engines/thoughts.py": "4adb9c8a9bcfe736cb42fff9b5ce24631da6ec473d178e83f1c176fde3b8b814",
+      "engraphis/factory.py": "be26899074d80b2f96fff9a5a70969894e818dc71e2cfdf4f7ee965f1f4cc550",
+      "engraphis/file_guard.py": "44eccaeca3afef7149bfdfea2321c325472253ee39a9e0bc24c720b3da3d685b",
+      "engraphis/graphdata.py": "f5dc93395f52203c66deaeec8bc58d5c1f990a35a535151e0b9a84cecf7d8430",
+      "engraphis/hosted_client.py": "5b56b0d2384cf24ecb409090af15f09e437ec8ab5a98bed931384daff46b4f48",
+      "engraphis/http_deadline.py": "bb29ac2d1e2fb49829e8484bb17f8abe98c23895ef17c68abe135d13f5df0099",
+      "engraphis/http_security.py": "5cd96551778d7a964ce1d87c6bce032a5e70c7a1779fb2f6731432b96f5f069b",
+      "engraphis/inspector/__init__.py": "720cac28b8a6019d0a0c53809d5905b7d6eb9d4ecbac767505904c6ec3c39071",
+      "engraphis/inspector/app.py": "8aefe8a935397dde3c6466e691a7e6a7203ebe42e07aa00c332b733465e59e04",
+      "engraphis/licensing.py": "7e73c28b0e1c3536e2080a129af614f838d2cae3ec3a48a3d8ed7e5153c9e935",
+      "engraphis/llm/__init__.py": "f3096d2ddd652b99e6fc0b4c5a8786d9bbaba41b259df0b44ce93b57bde3a8b1",
+      "engraphis/llm/client.py": "0c84000033d3f85b0e0161f100c271c35b591e1480701455ec65c7d3f111ec42",
+      "engraphis/local_auth.py": "8fd6d42594454d68c99bf25054adcfbf2379d4e08f17affd36af994fc7ad78bc",
+      "engraphis/logging_setup.py": "f7d2edc756458a852e0401453e9c71b785aba08fa7859aacbdc23fb30dc7982a",
+      "engraphis/managed_processing.py": "6d33cdfd10800d9552fcfae3c2b071d2b39fe10fb69d1a8e5d9ed6026882197e",
+      "engraphis/mcp_classic_cli.py": "778122b121a1c654b8f85810fad05d9c8d7799cf13903d7dc274938b51008da0",
+      "engraphis/mcp_cli.py": "f94e63805aa05cb913e48200819473b86b9623b2b958578f41f025adb0f1a21e",
+      "engraphis/mcp_http_cli.py": "c0605c53ff53ffde8d98d02ca2812e3c2c792a34e260b0a197433fb0ed2455af",
+      "engraphis/mcp_server.py": "b1a35b28e81ac44c0812d2569e662b1626704b00c7e6dce67cd70428cef25bea",
+      "engraphis/mcp_stdio_bridge.py": "a2e64883f4737415c633e9a69c1f3bdafe1860e1ee97d579dfc16814dd36c480",
+      "engraphis/models.py": "6e76e97db0aca3805c6f582ea78cc6e1c0ccd2665e16fd8ab81eb91b94141b51",
+      "engraphis/netutil.py": "15cd7c9d0792b5a95d0a722d94e433cf6d07182777f26bdf19f047270673b08b",
+      "engraphis/observability.py": "a3a6945bf33a0d8e216da56ca7efec0031b82dc64a66cff36f0b2161f5db4981",
+      "engraphis/obsidian_import.py": "cff5d117a592ceb8aa822e60a6142878da2f3aec1fcba44a5d64853c7bb0cee7",
+      "engraphis/private_state.py": "7485570efcaee8a1dc00b64ebfdc23178517235ae17609aa78db8bdda7e45fe3",
+      "engraphis/read_only_api.py": "dab1721cf39b7d374462002f5b770d53510a642d955eb4c9a972969e39841bf8",
+      "engraphis/redirector.py": "5ba964b81f09008c9369180cb49d247519000763274aabc5e046215b12fa641d",
+      "engraphis/routes/__init__.py": "f0d59080212cfa0d9b50877bca28e5832d1ae917899500d52c68b1c8821231af",
+      "engraphis/routes/memory.py": "9ca066e1762eeeaafd9790ed57d730efcaceb57742dbe0c830ad8764500ff9e5",
+      "engraphis/routes/v2_api.py": "a263af0f7d5be7d9a60a5c54129005705d02a0fa1ad3aba00c4b4667beb4fdab",
+      "engraphis/routes/vault.py": "503304c177cf4d81bec5a9836731c0c32b62159175dea6d0fb8ce30c97a2bc6b",
+      "engraphis/service.py": "dec62fa2912c19b13c904e1d7585babc5c55edfd995846f0bab33d62a20dff85",
+      "engraphis/service_context.py": "0cd84538ca18b07d6440fa4cb0147510eacef2af5cf04b7a0519f2ac15a7ff87",
+      "engraphis/stores/__init__.py": "48ee4326c8f28eecf46f558b7aea21adb779226a7038299017ab90196d5d84be",
+      "engraphis/stores/graph.py": "ebf603b54cf8450e7c9a7319bd05db2f39fcda8491f5969d6af3e8da61571bc2",
+      "engraphis/stores/ledger.py": "df5cbb30d977decc0a9c3a2365c9c115cfbb5fe951bae48446436661c80e5d30",
+      "engraphis/stores/vaults.py": "2c986129b9d1e7aab33e18a3b9a278eb5ad2236895587f69b5816a5d96796bc3",
+      "engraphis/stores/vectors.py": "45a1baca381fc647548cc89424eb36d5853f7562c275b191b35b99339a190b7d",
+      "engraphis/update_check.py": "ffbf5ef682fb15177915073ebc0b5eab4dee9092bbf0f58d36a8a54c6605ccf4",
+      "eval/__init__.py": "639f0c6d9d6aac8ff6dc605a34a0a301058905cc53bff4eaed5912247f0e7c56",
+      "eval/ablation.py": "16f159dee75d2f96cc42f230c2403fa19ea0bda7091c4823660da553463a194a",
+      "eval/adversarial_memory_security.py": "35dd8d981bcbad50e9815465be420b05b62a9dea28a78eb6cc1e09ec51c320c4",
+      "eval/agent_benchmarks.py": "8e88943e45a1b2083b366cbb0329326ef918b119a2366ed395c404c2b7ef98b0",
+      "eval/benchmark.py": "b71832affdf87d23bc1db7b522a669a7888571b3989b03a235c70f5da9952bd6",
+      "eval/benchmark_analysis.py": "1200791425d029695fee0b7da1f188a8962f337aa31eb4217d50e4503641d2b3",
+      "eval/benchmark_campaign.py": "033dbebfb47df5fcd3a6588b29ea4ab5fd44d4387ae45334379278ab30f3e57f",
+      "eval/campaign_adapters.py": "2bdb51de0dcdfceb1be2a649d84541780ac4d1fc0f9b7585004d87490073213e",
+      "eval/campaign_api.py": "323be4e1d9520e8047ab54c9cbb158013785402b06ee4e93e55227971c54bf95",
+      "eval/campaign_candidate.py": "88541840d16c3b7368586ed0ee3566054214b1f594826b746b28d0e407cb812a",
+      "eval/campaign_continuation.py": "7f77a20ac8f85cd96729bba0cf45872c98a3421af005bd735434b7b416dd7e1f",
+      "eval/campaign_ledger.py": "ba3079ba541cb1f70929a76f147d2bc5e8b264103a1cd7faad97685e0ecc7790",
+      "eval/campaign_oracle.py": "9ea5479786efd9caa2b59e612e891a93dd34b500a2b36aa20bcf749fb6d4d48a",
+      "eval/campaign_storage.py": "ebcd1f4aeceaa5ff9304494c64dd31fe31637ceb107d8cc39fa292e3b14055d4",
+      "eval/capacity_matrix.py": "8c25bd97754c1d7a8468a687042a3c87cc9c0299cf01c19b80dacfec2be4e552",
+      "eval/chunking_eval.py": "db5c39d98ad7272d25e2f33f39779da74a0d558798441561196bedbd38882e49",
+      "eval/closed_history.py": "beadb9dbfa97af2ca41efc737f41e8758f4c4635f468e6c7a2ac5c0c95f73f3d",
+      "eval/code_agent_ab.py": "d98bba6b77700ff6bf86ff0d2cf518a67e5a2676ef51bbddabbb2ff26e1f3aaa",
+      "eval/code_arm.py": "d211166fce1b8a4173848e1617873b7e84aadeff43746effe7483c54bbdb6f1d",
+      "eval/codex_oauth.py": "f235fca482de4201d1850bbfb583765ac5f1a057b4ad7e2d504d036bfc03f391",
+      "eval/coding_acceptance.py": "4b39cbcb60d7fba503cca597399cf9d04ad9567a43cdb950015ccf552e6a2773",
+      "eval/coding_corpus.py": "7b5205e8544578fe99d9d9cf6cfc34e40e5d1d049238d502ff7bc6f3c14948f5",
+      "eval/consolidation_ranking.py": "917b578d4e0bcb929bf1a1a37611acf7716a520c076abf4ade0d8d12a1c455de",
+      "eval/context_economy.py": "709ac7cc866855f96d7717ab2bea12e8b0d3a140d15fb978a2a929ad085931f2",
+      "eval/context_efficiency_guardrails.py": "22afd1a6fe17219e74701dc587ec35f569a5bf22bea270944525f51746723f14",
+      "eval/datasets/codemem.jsonl": "341313023c22850a2e14f02742b571ad1deca824f886a1654a59541304c01f3c",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--code_relationships.py": "969aa71235e0ae3cb764b9ee12b789184cedb5fea6fcc0d86e5dcb2c0498fa56",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--condition_values.py": "648702646fb62990168e98fba0dc6a27be128876548fa7035a59d71aee9da02d",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--corrections.py": "c7132c7fe39b7afbdf11065037369c0f3c38a22e69d8742e8afddfd5785d2e61",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--long_documents.py": "65dffb25944cb612872655f12db16af73f7a095e7abcf6a7cc5d31dc91f083b1",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--multilingual.py": "ff49874a691bfc30c082695ee6d3c89b9f2e1e5eecf086026110770d8e1b0452",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--paraphrases.py": "dbdcf5d7abf136aa5816df8465bfde842284aef5ef002e955cee05ae69d574ca",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--poisoning.py": "58b8ca4a37f55c4d112640414dc82620e32e643ab0aa539260884a5ecc50740f",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--scope_boundaries.py": "c1e92b10b40004c95abd3dfbada1a38fe0ce56300ecddca8360b51a1e6671458",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--temporal_history.py": "a64e4e5a29ce1040cf53e94571491325347f443d72a93f05bcf87c2878665952",
+      "eval/datasets/coding_memory_v1/oracles/atlas-green--unsupported_questions.py": "c8b415052ea7320e1df3c5475a676d4dd24602c45dbf1868fba6880846e029ee",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--code_relationships.py": "bb4305d15a81b4b4ef80b374acb59fee6fc32b213b101dd4b173ac4144d8570d",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--condition_values.py": "4bc5b1aff48ef6ad5ece1bd915f6949f72d365bb4815c4d82515b438bc644112",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--corrections.py": "7851502a9bc842f840bee1001e42140ee1df08be2730b563b1b197285d14742c",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--long_documents.py": "6204123eded20fc0c7aa59b312f8b5bd29aa88a720f7318e32b3c6a17651b57b",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--multilingual.py": "5c989b34fdad1e076b61ffb1f7a1371dc635f44a537abc743b765d5f6009004e",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--paraphrases.py": "fd189285d0cde9991dea461af9cd18b4203656a69da1298494fccf972ed8a58b",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--poisoning.py": "66305d69419736bdbb11a896543933604d898cd5394d94eedda8b92e632a09ac",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--scope_boundaries.py": "d9fbbe3924b5178f32f1937485af3b8db242a0e3a08c7bf41a3d2a57f34a8879",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--temporal_history.py": "7e7be0d6e558a71d3baad14a8812a6c998ad25e3f52c997a301333e0711f820e",
+      "eval/datasets/coding_memory_v1/oracles/atlas-north--unsupported_questions.py": "91f574dd678bf244a1fa6f9708e945259bb8ff8e2eb213426be5c3b187be3c3b",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--code_relationships.py": "d0998e13db38d1fae9be6d254431b4fe592f89eb03ee25705f4c70985cd48c89",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--condition_values.py": "f97610aee190dca03b01aa48ffe4aa3f75e099a59fdd867db98f743f4a376729",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--corrections.py": "b7c31f7a9a1f978321ca5445997e0d284deea770c85f6d81a80204e548ad53ea",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--long_documents.py": "20ec2b41cd3b6691164bce096dff16f7bf5be674f922cb637120c0347e60d0b6",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--multilingual.py": "131e7dc978d3f2f7df395b6f1b4a9150051c0ca93c6dc5c386e58d46c8fdc573",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--paraphrases.py": "1e7d9da36e6634ca2d2b11dc97468bd671df133345dcb76859e1dc3cb77dc664",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--poisoning.py": "48460691ac0086c47102eec85387ac03bee9190ac83e3dafc4babc79b71d9bd7",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--scope_boundaries.py": "b96207e9b1fd09f49218102a5b88fde5b9656604df4cfd314e86426e3b6d6075",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--temporal_history.py": "7a196ff9a1db05b0c8f3a83086ae44cdc580dc58e4acc217d1db2575d9711b88",
+      "eval/datasets/coding_memory_v1/oracles/atlas-violet--unsupported_questions.py": "724564b5b75b9425b6889faae6d5e650bd5c940016c2b96054e5359d9d8b0887",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--code_relationships.py": "14295f735bcac4d4ae738eedfbd8fad4593afc914bc835233ec35e2263d43613",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--condition_values.py": "8ac70d9ca0c9122567bb9986d2cc5798104966df20e262b8087920e8fb5d82a2",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--corrections.py": "89d6a1a7781465c311830b7e769d2a76df41ab5c703ff662b3df1cc4c9a01668",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--long_documents.py": "38e67a26f69707089f852657a810ef1fca0395beb5511fff67c30f21ed63df57",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--multilingual.py": "bccf6579681d45940542ccb1f936ea1b225f4cf551a3ef31f3f8b1a026856e51",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--paraphrases.py": "89c8ce16c682553b27652e176b67a06f3228ae6209fbc8a7264260680f5651a9",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--poisoning.py": "fe9beb97d27eacdd87056fa1c9b04c62e2facae9354e765b912de60b35021621",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--scope_boundaries.py": "2eb3b1130c54644fcbade52da8f50cad1376a07b51856a962522913cbcbb7649",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--temporal_history.py": "116ee20af475da329cb535b0a02bd19ea1e7518b5b780ec12ba396ec896cc116",
+      "eval/datasets/coding_memory_v1/oracles/atlas-west--unsupported_questions.py": "080969e026215b9fe4ede6d0b4d02e9143e1293bea5d7383681e478426ddf121",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--code_relationships.py": "3965671e5e2432c8236c250f7982d4f478d8f1fe1268ffe57c555cf5fbbcd414",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--condition_values.py": "92994990327445258984ee6bf1d95f47359ff4b194e1f36e193980a523e6c5e0",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--corrections.py": "c5b473f962deacd6d59ea9967626e029888abbdb48f320704bcb6de876ce3f46",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--long_documents.py": "54aee2c1031c17b5678db2b0955eda8fafe5990aa9e52f02936584a9b75b9ab1",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--multilingual.py": "c458ac5c63e440e3d9486d096278759920d636f73e1901258679251afd86eb60",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--paraphrases.py": "250d027660f268cef1caa745cf3155de6e2f4adfaed02ba675eaa83224ffeee8",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--poisoning.py": "978f16eb5033c602ec09ed57ba0667edec9ac3e26accc1ce1456bc893ac9e6a7",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--scope_boundaries.py": "4b73a2e5dc5ac815c14e08a34acefd2ad426282cfae379ca2fd3060a3784c9b7",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--temporal_history.py": "6636d511bbcca51ca85c4eb0ec5ae956b3baaa5f9af89458ceb86329115743bd",
+      "eval/datasets/coding_memory_v1/oracles/borealis-green--unsupported_questions.py": "5cd4f70627bc60572c720a797bff122ef9bf219f32d265f694affa33b1f9f4fe",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--code_relationships.py": "769903aeac3ce360d845ddf1a6e89192737dbb460e1f2e251230b74d40763dd6",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--condition_values.py": "f6e69f525fd240a09152989b9d8a529e9abe076e7fc2c98d10bd84f9c6da2b56",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--corrections.py": "987ece1c7507a69a973c1e051b27c1d3b104ecda79df48959e49a62da31aa137",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--long_documents.py": "011134140cc486a3c089b407adbfbf5b958e1f8c1bffd572c29b8cd5d7f07f7a",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--multilingual.py": "1d29536a4a5836f64f56adcd1a965db85bc3371a12ad5bbb5644520c9d9606c8",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--paraphrases.py": "09a5fad90c24f75f2f448854c8778aab896c67854c97f884c2d689ead808583e",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--poisoning.py": "c1bec2ed9b31103e39db9dbab2be8db401cb0874bb3ce8573a0841a054e28a46",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--scope_boundaries.py": "faf51b368d7ba9406442edde29e290c931e67bff2799783dfd27f2226020e15b",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--temporal_history.py": "da52f43530149a4a293065674623fa49f83b37cd84b9871044b3bf32762fd8c1",
+      "eval/datasets/coding_memory_v1/oracles/borealis-north--unsupported_questions.py": "be0abc698692c9fe82f40f76a4694c472882a53843894dddd631ab1ab77aae45",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--code_relationships.py": "9497b7d2373bb9f858e994f7919cff72e7e3c4c4eaa1efda287524b1a182d1f4",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--condition_values.py": "aea13e4b7721019e7bc1f54878bb25b9f27a8a5044fe444e86ba5460deb13e09",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--corrections.py": "bfd446d431afb6c05ad9d8775b90887947b85981037756e05262f3b101d41e7b",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--long_documents.py": "eae829a374c0cd6237fac4ec52fec0d98d7340ec0b307b9b0b0c90c116d4b472",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--multilingual.py": "e821f91999b5f12cff53fdaa956af4e0bb2f929497f95b4e2ceb57a6621e58f7",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--paraphrases.py": "1a99c15898831a1c9aacab951868101d57e59e91ed90a2777015a26dbcc3043c",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--poisoning.py": "411877fc07b053201a63aa4e45cb499344abccb0a562c236d53a672078b1eb63",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--scope_boundaries.py": "b198dfb636910953ba372edf1cd6db382d4e5725bf7f820171be8c63f9fedf7d",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--temporal_history.py": "3de5efd6ef661572191c6aa426fb10caf9f4bed4aa495b6298815aab3acdce22",
+      "eval/datasets/coding_memory_v1/oracles/borealis-violet--unsupported_questions.py": "baf5dd85e86a97dedb0b395b5c574ea5ffcdad7a46bbbe9787cfdc33d6c7a06c",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--code_relationships.py": "48e53b3a561f91fdf4eedb2d63aad65eece8ae80188bb3d5bdcaf184fb0b6945",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--condition_values.py": "2dd7a524bd2a2aa2fbf212246880d4e4ecf03f503b70f25179f3ab6bab28a07a",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--corrections.py": "7d3080e05544e10243040fe0a969a8c524e4262f8f5c38abdc3d8e06c67fdabd",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--long_documents.py": "fc42e935879e7a81f6eef9fe72f8683244501ae10654008a7863d397ee73058c",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--multilingual.py": "19181c442ce5f6941485190ecf050e455914dae988f86efa42665cdef0d835a2",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--paraphrases.py": "f7a5cb842aae3d2bc8d62ea40325b332a8bd4f013b76bac8bf154fedb3dbcbe1",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--poisoning.py": "285a2526a6be4e556a564899e9a376ae1286fef6f0ad22eb9289fba1905a2b68",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--scope_boundaries.py": "fb994823743ff5b4853b142c17779778bdb11296958e033e5c6be598833a4cf5",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--temporal_history.py": "f30a74c85ad654a7450e20d07baceb3b4fb2a56b454d7b43b854bef3cdb2cee6",
+      "eval/datasets/coding_memory_v1/oracles/borealis-west--unsupported_questions.py": "01cbbd0b21a745720514aea6a21a98a3cccdbf0c0518bd5508019433b964776b",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--code_relationships.py": "8b08e7c65289515a9eee2ae5f4cd60ce94350e9a561225bef0e8f8815ea28f79",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--condition_values.py": "92e7d75d38f5dbcc685075e947005a9ae5a410207e7f17aa770b034b8690cbe5",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--corrections.py": "424cbf0924a8cbc1a59a6d7bc82b5527e41f52c8ee9f558ea3e398ab4d913919",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--long_documents.py": "2a52df9cef3ee66357847322794a382c927b828c6ab1a2819a799ff55d53657b",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--multilingual.py": "e47e791dd15b045a6a958ca114b1359ca8537e160274b015214746a2564363c6",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--paraphrases.py": "9e92a79ec00231cb381ce58e389dfdb2520a17ecf1e9c2e39e79501449e9ddd0",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--poisoning.py": "33213e6f194332969da88f4748c8f26ef93219b6c4bc710a142082f8147ccfcc",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--scope_boundaries.py": "8d2489da1fba137981e45e42c843f9cbd17e851c82ddcdc5904b4a86af0d9692",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--temporal_history.py": "29403fd08f0de7da3dfcc6c181e1f448a5c5264e95ff3924f3066508d85468b1",
+      "eval/datasets/coding_memory_v1/oracles/cinder-green--unsupported_questions.py": "ba21014188f9ae849e0bb79babe163194703c4cf01f0600f4c9f71058e7fed56",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--code_relationships.py": "46280659557bd08afff185352438bb63dfd308dabf5c7c1862c2f442bd171d48",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--condition_values.py": "6c62d673b1b6cb4b5c89ff2af4ecf57c2c9d73074a01ab92b8fde57815cab783",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--corrections.py": "8245b196072389517fad6d76ed7709d7e12eb52e08732e4ddcfc40fc1d986879",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--long_documents.py": "6790c7b89d80ab909d9e1a31b59bfa5cd199cddabed2e159daf7c5c049ff9a43",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--multilingual.py": "9532bbd14506cac0edcc09f474e7c96a402903de947e0e76f5c8aab4bff37646",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--paraphrases.py": "cc904350ae7d40e26d91d482ac15d87ec8022d4c82905021dd38003c5fa2d067",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--poisoning.py": "e8e451c49c98744b4a484141f86d337db4ec5326264b1500893a20c3451c5ae4",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--scope_boundaries.py": "50d42fc48aa70d55b6a3b39c9bf17437726f37e1e5ae9870d415fccad92c7bae",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--temporal_history.py": "14b1336fbaed11cad455f588bbe078effc31f5f357f670e1f189ec3d78b172f5",
+      "eval/datasets/coding_memory_v1/oracles/cinder-north--unsupported_questions.py": "0a2f740700a990d22b4c3051aa3e4260e3df4ce65931d419052f74e05c750a67",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--code_relationships.py": "0e29053f11fe618c01fa90a274688f18ba8a7f3cfea56757a96d5a5bc95b61a8",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--condition_values.py": "ca57ac4e22e9b4739217020d7792ac642326935b8db9305ead2ec5bea2a6e456",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--corrections.py": "9edbfaa58a99776e835c325e50a77df5b4b302b3ddd0932dc2a349a77b4100b5",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--long_documents.py": "4b3fbe7380201285ac4b4a1ec4d8238c5663b97af01cbdc8ffff8fdf2a9467c5",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--multilingual.py": "b0bba5ecf669f3368ef29373b755dc1296502665584574c771ebf4664debb5ce",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--paraphrases.py": "e146f7aa1ffabf3b313251b59c59e1836c0cd17901d07fc6ef5334eaccf8bf36",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--poisoning.py": "692ee07e750fb08652a1ca6bc6dcbbef77219701585f1336c6037dae5a7c5767",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--scope_boundaries.py": "8ca0b911d38a72e4ecce6871ba3d0c7dbab433b0541cb64b116f7a88d521554c",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--temporal_history.py": "6ba5400c5435af64c80a7366fdf49fea132f1011f9d84f9d0cc5f2f2f30a67ac",
+      "eval/datasets/coding_memory_v1/oracles/cinder-violet--unsupported_questions.py": "1d3324db0a085be30ce3dff1a2ec3866b8592a5ef6b43f39211a2e3a59fc1cd6",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--code_relationships.py": "0149333a3fb0f8d60939bf927921305eae447f7511c74f042ff3c880eadff825",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--condition_values.py": "3158243f9f7f0b92aaee4164379159b46143acd11fc3d41a708630c1d33ea22c",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--corrections.py": "a9fbb89aa629a23e7a1fddf4fca09da40365bbc7a9a6192d805e498fe17f93ff",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--long_documents.py": "3c702c653a8ddff84eb5c24a77567aa63d2069c48ed174bcf29065c0ddb30ec6",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--multilingual.py": "b8f5f7e00e6edac3f8e0b7e8bc09ea6c7d661370fa2226eb1795306ce3c634a7",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--paraphrases.py": "10361be87e9d9cb98d2ff1bbc18252178d475a5c5f2efb77bc81dea05109df05",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--poisoning.py": "889a5a43604f7d1677ee0f28683abfc48a8a597b052f558c1b4d19c5f33444ec",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--scope_boundaries.py": "b84e78812baaa92422226c06d78cfe7c1be260e2bfcf9c5bb1ed73f2f3cc136b",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--temporal_history.py": "9d99a981fca0c801a0a52e2af24cd4262dad72f4f34cd84894784285d241bd05",
+      "eval/datasets/coding_memory_v1/oracles/cinder-west--unsupported_questions.py": "43b8f854961d9cca5cb83b53b9e07d22388d0c7db406dc8e4f8cfdaa5f89fffd",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--code_relationships.py": "97a08f2bf9b1a11f95a062f7df27d69db3e9dbc421837347acfe62111af02885",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--condition_values.py": "5e53695288b84a526c61b748b170f6d6219f94a942edc0887ea6157535ad8d52",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--corrections.py": "c6d16232ebe6bdb0b5c94db1ba4f108257b47ee8f8b96cda5f8e17212022b542",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--long_documents.py": "bedb6f495437beada344ce6cdd92954108aa4c639622fd1cc294d2a1139b26d9",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--multilingual.py": "dbf84f4e8c016c5e60fdac5fd3ac2faf79fb0534f5c2ac534491acc31d5f3530",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--paraphrases.py": "ea8f00c86e8fbc2ab10a448f48019146181d0e55438def6f47f41f0ef3181be4",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--poisoning.py": "4eb4e289e944e7762c39ce85a8fc2582e310de6a86cbc1cc36b44112653140ea",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--scope_boundaries.py": "2fe9b96deecfb488430abd9657adc6b3ea092b18f32c41c1669d29175ec6e860",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--temporal_history.py": "531cbb953400584356cb6525bc1a2e559f7ec3867d845c736d8026a046b91e7d",
+      "eval/datasets/coding_memory_v1/oracles/delta-green--unsupported_questions.py": "edebf25c2168411fdefae1307a71d829224dba3dbc7ea000054416e52123d5a3",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--code_relationships.py": "9357ad0d5f6a1cc787f980d0d506b07808538179f71ae3e8ce1c3eb655d24e35",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--condition_values.py": "4199f7409696a260b1531f4ec7cfd15555b4d58d06b0b8a88b1c7621fe7d328b",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--corrections.py": "b8bd58db7c5ae93d33e6223cc34f0e09d58831361ac013ec08277fe2c102ac17",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--long_documents.py": "0f08b744446b1c52e8fe86626ab05c171377f17c46e604cb2ea647ed5d0daddd",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--multilingual.py": "ada9eb404190d05637cea59e3f8ed541aea2c9e0f9be0d166885d6789351f7a3",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--paraphrases.py": "04ec2e8308f47f46e38c89f4a2fe44deef4a0b20a1c8517395ad00983bf7361c",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--poisoning.py": "d72ea7b98db47e4de03884e2786206dc3da5cc08e5203c86b1d38a2d48c2fd47",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--scope_boundaries.py": "cedb3234b22a40a7b889f50cfb5751fbba31e46f541b19feb2c4759c8007bac3",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--temporal_history.py": "2f7c1bd4ebc051eee411d11251aff2ee5fee602a0800410bc0dbd2e86e99628b",
+      "eval/datasets/coding_memory_v1/oracles/delta-north--unsupported_questions.py": "f1f0b9858c806956122144c6e769f3baf9f87f07ff92eec98eb58d8019e6fba2",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--code_relationships.py": "79579639a60d96365781e853d1319a2bf85d9a2b4d8639410da7e3c1efc364b2",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--condition_values.py": "27defbfe7c237f971ae29e8f000f098eae32a11f3afad06f2bf3b27af432d902",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--corrections.py": "b3b685a5c33d1086e8ab4258d26c5ec9aa7396b8250a250351f0a6057fcf2075",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--long_documents.py": "4a5ce75372c8762bcd7986f8ceef454800c3636124ffd9de3a8315d210ae85f1",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--multilingual.py": "7ef19f25e97a24522b79a9d7e7f3d2d9e395a1fc2c60564e2f66081533bdacb5",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--paraphrases.py": "b6e00019bead0a5bc0facdac886b48fccfd3cccaa254267fda780e933d57904f",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--poisoning.py": "3e3e1e1fe04ae3e0c615ca21e794fead5d06f887d6fe7347fb9122684c8b8017",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--scope_boundaries.py": "336ae66910d533344712a2d87126f53df48d43eae9e7d17797938c3f9c560204",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--temporal_history.py": "a81cb5d2a5eb521dfd161ffbd21bd366777b1239f2d3412acc77b0a9c7c7d82b",
+      "eval/datasets/coding_memory_v1/oracles/delta-violet--unsupported_questions.py": "3341895608073374b98e67a88489abb9020fed5bb692231a0a61e15c8de0ddf1",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--code_relationships.py": "e8f17f3838cb74e1ade0cfd6edf540dc086507b51ca67c2020ed490d75dbffe5",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--condition_values.py": "a935a6e7a4081737eef76a93d54b34dc885b4699e02d797f1be78286dd642a2b",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--corrections.py": "ee407e5aa8d57254bb7029d537bb2b59a297958cdff9bf271de3787b6448241e",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--long_documents.py": "55fa08b75982d0547f0c2f13cdc6522d0fbd33efb4af9ae8c6ada11b2d46f321",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--multilingual.py": "ce8a3e45ad8417ca1798579a22e12eeb7d170a11ebfb865746388eb0e7dca848",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--paraphrases.py": "e6458588e20e76596e24be6cc838bd4b0d5a47b05b7bf0bb6017b0cecd0d6a68",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--poisoning.py": "4c70955a2650d13eba24d6e933f765e0bd40da0a1cd8b920416989a76bdaf2d7",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--scope_boundaries.py": "cfe9120c49224b6f9ed86ea7d85e496000bef0648c92c7fd474c540e892863cd",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--temporal_history.py": "3527edc8a85c71f889ff0b2ac8bf9ab005ad5bb6c95bcd917dedae44aa3efc72",
+      "eval/datasets/coding_memory_v1/oracles/delta-west--unsupported_questions.py": "8c40923b8d4bd6bfc78ff6548ef9a840319b7ee4ea967554f26a8d24a4349935",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--code_relationships.py": "cc7f82ad85363ee35ccd75744159bf4c4f07965e396bff07989cca7a55071679",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--condition_values.py": "3fa888c125812f1488de9e021358cd531a9d50bb7d4b6173be3656268474b635",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--corrections.py": "7cc639d4bd7b287ed0e3f2188491d6e4866e021b21874b34b365c1eb2b2d6d68",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--long_documents.py": "972e7879a30ab26f86f09bce6dc9853c7f96124d0bbe5062111607496bcc9a95",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--multilingual.py": "0f0585bd3264de3d5fed5928b54ff4fb87f71b2edb1d35c83a534251121124b4",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--paraphrases.py": "a3c15541bb87cc862d1c9764cfdc1ffebbc831876b55167470ecb3b66519740a",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--poisoning.py": "ace5b7b12c4ca068739af4bc5e215af1af7fe153399ff17ffb7a67b8b9aa1f94",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--scope_boundaries.py": "daf132e130c5743d67129c1564f329fbb2670d1242648920b646a83bc2236e4b",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--temporal_history.py": "1438f09f0ae41b1f6b42930518203a36c7de31a870b684dbb7f16e71a37c784b",
+      "eval/datasets/coding_memory_v1/oracles/ember-green--unsupported_questions.py": "da27396afbc1529c61972f739cefb26dcaf97bea529c084518a95080eac4fe78",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--code_relationships.py": "debaf885151c3f47660053ff50e015338b8aa9bca089d7e901ee8bc34f7085e6",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--condition_values.py": "109a7ee90c04da83f57a94a9a724dcf98a3e96405c7a456686c198ff5d85a69c",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--corrections.py": "c246ba011c68d3ad0a4ee1d14231304a7f17f28027f1764e60da93062cf1cd3c",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--long_documents.py": "176200cf2a011c7231ed4cadacbe86b1eeb695fbbee282bf4c4a96430d98fe84",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--multilingual.py": "e850a910515e71a27edff26f7bedf39d8cb75c726e48357a2c41d4da051be6e9",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--paraphrases.py": "0a6f03310e44abcf4ca61d69e22edbd21ce47a17629adf4f5079f7565534b469",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--poisoning.py": "a81ee758fc57bcc58bf0bf2a38dae8b6eb4aeb14949063206e32cdff6f301dfb",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--scope_boundaries.py": "fe42df24612c66b175f1c98794ed9f13a1a7819418e4aeb5ff98531515221de1",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--temporal_history.py": "410f9770097228724a5af1357003ea23caefe1226275d030d46efa535c42d306",
+      "eval/datasets/coding_memory_v1/oracles/ember-north--unsupported_questions.py": "eebe43443938693a74081661d2ff3733b39c6dac5c7ecd88c4dbab5ad18689ee",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--code_relationships.py": "c00a30669fbd1c740b44e17c7c7369582c28a16da3aeec9d27420b8aef7c553a",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--condition_values.py": "1645e7c56c870f4367c263ccc9041181b1d187a698252203ca651235db59e684",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--corrections.py": "735f1d125d2ade6f3eabbf1082a408fe6afd4328cd954833e23df275df498e37",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--long_documents.py": "e1ded8e9641639443a6b14da18b2e0cbcddc6fc6045bf0b57404b59b59327dce",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--multilingual.py": "fbf04cda8e1231c7ac4c64d4c1856f7bfafcb6f1d016de0b1bdbbaaafcfe03b6",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--paraphrases.py": "2fd495def306778073df30b20dbc7a1500c06c90638acf6d9b9280db78dec53a",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--poisoning.py": "335674216a418254a01a7f5505344af20ad499a5fe41cb9c8654a0705574a18e",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--scope_boundaries.py": "078d60287888903e90343d144d8f54e08a3751ffcba82fd827ca0c9f8ee75fe7",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--temporal_history.py": "f7ad47f3253fe922977cbd0b63679abf00559f1b2dc895246e09840652b2c41b",
+      "eval/datasets/coding_memory_v1/oracles/ember-violet--unsupported_questions.py": "b91545082a31952351bc4c08d6cc09132432126dfd772952c818396bd7a68af1",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--code_relationships.py": "74fb3e0d99a5bd4f54b8b57f6040ce7978a81bffa1ae70f9069fb2322e6ea581",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--condition_values.py": "26d605b42d18cf029dfdc29124eea898e0dfa5642c43c1c775007fb443ba6cda",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--corrections.py": "65c2ef8544b42ecb6b3ea9ce8bc95ec5f0ea8bb07c2b74d52e7880d99962f563",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--long_documents.py": "4c8e54c7ec930d6cc782fa1a0519a0f1e0e916e3929902e13199775cefdaf338",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--multilingual.py": "356e407f47d39e7f53337ffc4f27c68935a2c831301dc3dd006b2939cc61decd",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--paraphrases.py": "c91cf574cf8b5aadaa6c9331c3f8f4a8fec7ec33c227f20894f463d81d110a7d",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--poisoning.py": "5f6b8740798a7a093994748ef4b11e0e1de0be562c7f09790e1f0ebb9ed21f7d",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--scope_boundaries.py": "5e20c5154818cc29b7e71444054d67836eddc882f2f17be8aed78afe31a9037f",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--temporal_history.py": "fc51d1a39693d1f7fb2db4bf1ffe865d4c44848c159188cdcfda54618c0d8fe2",
+      "eval/datasets/coding_memory_v1/oracles/ember-west--unsupported_questions.py": "079c421cae974bcccc2107dac74421dd5bc2d1b40f7d91cb79a8014af526d260",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--code_relationships.py": "b5e4a284bad1d7ff81d5be9cf1faaaaf5e718cb51624189482624721cb459f1b",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--condition_values.py": "63c152b8da5655ae5c701cbb51099340d5f5103fcc47840239098a7366d24151",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--corrections.py": "b7b33b8de153c205ff4fdaadd5538eae8a22fd4401e70db9f645dae205c62cba",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--long_documents.py": "624cf014bc795a24e2f1f4fa2f9dbf11d2ad1c38f81cbc58ab3948f96c48c8c4",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--multilingual.py": "f8d2483fd9266946c980764feba0eda27c95ea2ff11222a4dd4247fb537f1f00",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--paraphrases.py": "151be253b730d5c5b4bbcabcce3bd218477241ebf0f1bd5fe9dc8d70798feb6f",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--poisoning.py": "e7b0efca3813bbb1d4ea9cefa752b4318942b118bb61ee9dcbbf640daa66644d",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--scope_boundaries.py": "56177cfb45f32c548be83cc78197fcf5b53826f01cca69e471535476184ae8f9",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--temporal_history.py": "2c79d26467eb8443d743bb8823cc1f2a5d1e5da7c887754505baa130e37f1b2e",
+      "eval/datasets/coding_memory_v1/oracles/fjord-green--unsupported_questions.py": "fb5f222f4e0715379591f559036c0549f67a7b6e3491e880c6cf8d5b91fa9000",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--code_relationships.py": "07402078200db9ab15fc61a72e31d9df0938edfb1e9d5b7e532b422dccab15aa",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--condition_values.py": "8c1549b5a444c9cbf1304fcca13b79263bf8d9f0b4f41c16da539b3bf5da3bf4",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--corrections.py": "a2634af73134c025de1b6239756ee2051e505e0a535221947babef5ba161fa13",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--long_documents.py": "4f80f3673afd1320d16a6bd45fefc85522d6f4bb889ff96f6e99410580feec09",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--multilingual.py": "3a9c953fbe76eb7374992a6a81d35b8dc0a635c02b90f328af140bbda2acc180",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--paraphrases.py": "ec2d9d7bbd678be73946cba8177184839505cd891df410ae8e676fc254df2ca5",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--poisoning.py": "6d9b91b4d53925d58d3c0cea694f591572a53184f23816101af0aa644aa1b86d",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--scope_boundaries.py": "2e98afa064e8a295a78bea654014a92734696a235fb0538732bb8d85799c7287",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--temporal_history.py": "4059ab8e427c2b6fd68155992404fbf493c7ebdf0a4357aa5c5f4ff0c67808f9",
+      "eval/datasets/coding_memory_v1/oracles/fjord-north--unsupported_questions.py": "79f14e18e282c1b6bbe21ef2affc9dd8a259a171c2e4975d42363f7c91689c1e",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--code_relationships.py": "9ea8a9ade1001bcd43929782c3410f35fc5056e438342ca848fe0b1b0ff56170",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--condition_values.py": "09e223a1c0bff6c95a5863fdc28dc00ed96b90887cd635d014712058079ccbfe",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--corrections.py": "f822c373fc4a93189fdce09999a9dcbe8797b0c0dc780eddd4e342edf21dc14e",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--long_documents.py": "983aeaae1e14937a740218228778be3e1938cdf1ff9228eba44064336188f297",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--multilingual.py": "6e929f8846cfc756c71bcc21bc0f27ef8fc23270d21292fc35d70e6bbd31c066",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--paraphrases.py": "c644d9f01edbd213447618bc269f56804450901faf4f4660c1f666d4e9b4ada4",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--poisoning.py": "cf3849312f96b0072efdfd4e858abb24d7e6a808bf883bcc9dde5dd5a4594364",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--scope_boundaries.py": "373d10e20713bdc26849706525f765f2be4ab57e87e576e39a1a1dd4e7feed88",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--temporal_history.py": "4d2c36480cc04d43aa8f535bf998968b474f2f596d5349dcd42684c5a667c6a4",
+      "eval/datasets/coding_memory_v1/oracles/fjord-violet--unsupported_questions.py": "b381d2016dea525eebd8de8d026dc48ad2080b93823a95d6e2bb06d29cc86775",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--code_relationships.py": "e1e10ed9ee8a4d5c2e798c2bf04cba5c39eaa3873901bd93724af166ba2479ae",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--condition_values.py": "427764a62d2e11f6c9fe4b2cdcd32fa92f61749403dff648601a47187e38787a",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--corrections.py": "4aa041aa87f4c8628d113bab855a151c2e38bd6919cd02224827fd07d060fb34",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--long_documents.py": "89875548e6952ce810d8983b0eaf2724bf8f329bf44e4d9193cfa3405e1ce80e",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--multilingual.py": "8b5c14cdb26941d1ae25701bc99efc5fe4ae6e50fed3c65b193952444f1593d1",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--paraphrases.py": "bcdc9a5f1fe45ef63fd5e6b728c83c7a8d05c7b80957e3276c074700b409e924",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--poisoning.py": "5504e1bab0865fb3041c88f151938789d79422eff91a3ce72f4a41fc14e2f897",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--scope_boundaries.py": "63f226631a663dca0ef62a4f32bb98fbe1e30e3b1f030ee42c3f7f2bf6a09af0",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--temporal_history.py": "75c9582a16db2c89f12506bd7a4115fcd871c6da63e80429a8e70e31c1f5f862",
+      "eval/datasets/coding_memory_v1/oracles/fjord-west--unsupported_questions.py": "05e4ba65be7cb4e6500af5e14721c70f93fd7390abe58a60f6f8e4f8e9b0ae5c",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--code_relationships.py": "bd5619518e839f84ca03297c4f7842a2944d8b445ec1863a8dfc68e4c2114a03",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--condition_values.py": "67377847b6ff1ab865f5c25351fcfa1ee13e6ec6a089444cb3eb0709b660148b",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--corrections.py": "c07e8a03c6c47818f9c574d4f21b27668989711fb5e0af3b5cf1a87b293abcbd",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--long_documents.py": "3f75fc2158c66a19dbbd19209fc80026339abe93a2282ff55c7c01429ac549f3",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--multilingual.py": "19b1f800b38a11cf0f50df6da3a011806098561e32a279b78e1806de9b8c11fb",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--paraphrases.py": "a5996376b9f589283dbe301dd1e0644af92a8b6a0222b51b99ed6fbb83570782",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--poisoning.py": "c4dee0969e39b52dc9b697e45587c8cd84926a97c9a48f7211c0a00571bfb657",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--scope_boundaries.py": "8d45422f0a1a2115deb90f560409fdad1105b7cae1f03052f8ebac404ba9517c",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--temporal_history.py": "abc1b386173c8252ac10f11a36fbcdd6d91c731686108a6d32c62d17955d21b9",
+      "eval/datasets/coding_memory_v1/oracles/grove-green--unsupported_questions.py": "1ee09741a1c94a1fa83c7edf5b6c07d8da2e45826f748d899ec71917e8369d54",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--code_relationships.py": "fd75d734a5f45a5ec54b125c1d379df67c5531659f212a2f5c1c5e88169167e0",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--condition_values.py": "c600c0e5f50e352406b99527b050f4df6dc8ab8920b5b946de190ad7629b5e6d",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--corrections.py": "4d6fdbe4f5eb9c8e4bfc2a974e6c3cbf1d124d0b20d3f050c84e766f507b4be7",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--long_documents.py": "5b0bbb9f0a90eb377cbfe45ff6f37077a9ce32c7c6730720f0bfd49b844fdf4b",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--multilingual.py": "525ea2fdad66d66d7b90892e9424ebae281c1dabfb49f2668784a687b7ec894e",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--paraphrases.py": "1105e52a8c8d3ff79c64b59ec5f23d66d742b8dcecf91e8e62060895c7371f4a",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--poisoning.py": "7d32e533f6dac57e5d651868386686d2b78e7db1cc29b1860fede23fc9c49813",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--scope_boundaries.py": "7bea4129589ea34ba10667a7035b126a32b423ec7f3b1ff2b10f6ffc9aa1c2ee",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--temporal_history.py": "859b6504250f5746ce197e4a0a7c1006f1c2257b939c53a493f9d36f6d2b7d6a",
+      "eval/datasets/coding_memory_v1/oracles/grove-north--unsupported_questions.py": "6b893c4c124f071e9ad5d9946448b070c2b2f5f10da6f058e60840c18510fd0f",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--code_relationships.py": "09bb7df6b115b83cb98a4274b2d883e81b809643ed4f912b383a9e09a7f7a1f9",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--condition_values.py": "a68c126f0d7b2fc0950baa5df095d7d513cdb8359883404bad3c1c84c8de666d",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--corrections.py": "46024b5fb187aaf3574d380af1a3bb2aa44028f89377f810ca5e98ee03c3b9aa",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--long_documents.py": "ec8d401f6437fbaa3b11ddb96973b31944ff374da677f7aae26c0e79e6a1315b",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--multilingual.py": "d14e8bf66593ceab7b691119b8a82f211933e2b3f6ebf8a25a75e61ffedbc1c0",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--paraphrases.py": "963b7321a32931f238d12e7cdc3849f64682c7cb704b77f4b849543cc40b6df0",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--poisoning.py": "39e5edc76a122d37d90b1af28c2293e2f8b0c38e1bdb6460340c0bc2a71ad87d",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--scope_boundaries.py": "472298607415aedfb9a36bad7783e7b7e3bccc339ee44cd83746d782ca99e411",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--temporal_history.py": "dcf793210a0a547c25587bba70e01d4d56576604856ed084eb5fa466b8be7b83",
+      "eval/datasets/coding_memory_v1/oracles/grove-violet--unsupported_questions.py": "bbe1769dc0afbe220e8069ef21b85164c31ecff6c3c7f5bf6d18d1e48f5f3c72",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--code_relationships.py": "5374fb66cd91be79b5eabd2696ada5fee89605d8a1fc84ce36bd6a8ca82cbe5e",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--condition_values.py": "2e807846b760b65afe0f5e48947463a66c15b8d89899a2724cddd865311760b0",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--corrections.py": "bca219aae5f85e3f5504d5b39646efe89ff7dc6c007a4323abd5c5154cb4d5a9",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--long_documents.py": "19c3ca44f78ef79ca1b907c80214e11a8195e994893f1de683b5d9796eb29d6b",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--multilingual.py": "7842efb41f88fcd49e7a2350e9b44a3a1946bf73e5cb103e4a91a11e810301a2",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--paraphrases.py": "fd70e8a20da665073ad172219bd57b24e53575dccc344adc1fa0190770ffc6cd",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--poisoning.py": "473acfa06852554dee20445dd1a86df4e626e0363a7b72de57d68819314bf938",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--scope_boundaries.py": "3ba0e93abf07498c570cd81b0c4f753bb75b6d4f4bf6c786461bad1a3b301286",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--temporal_history.py": "334bc7b057f570efd20896d282e54c986f5b6c642930057c8520f84b721ed5e9",
+      "eval/datasets/coding_memory_v1/oracles/grove-west--unsupported_questions.py": "5102eb2dadcce0dcc0ba157495d4fa10c4983e4bf6627aff25bbd547a08115ca",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--code_relationships.py": "d376cda89c44b3282a86afe7cd01583f0b53f2c80cd92b47bc2fa4a19271e9ee",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--condition_values.py": "7b6eaf2f46a5b2f1ae6e8e6da0bcfe6044fea5639df158e137fb8ba32b929909",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--corrections.py": "2e849f6c926aa0ce1b2e69ce8cdc5ba9c50feb89b33b257fc71bf3aa3b8461b8",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--long_documents.py": "884c17b7d20d986708c0eff2821cc7b76c5f7b16afd26c43ca80fb507e2f3ea7",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--multilingual.py": "1182048aef0dcfbc416a004bc43f49f1d2a5de4132e7243ab7d147f54aab1acc",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--paraphrases.py": "a73950ae7fceacfaa6c7c7a26c8379f9164a29ebea883cede9222e72c506db5e",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--poisoning.py": "60c5112afb7b84ee5513f2657f42d0eacb0607ba345c28618af3b3b3eaab753e",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--scope_boundaries.py": "dab035b811e7e9a60bf447d1ea26f6db915c320b5dc2dd04cda4b6f1023296be",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--temporal_history.py": "c22dd57bc7cd659863231b164192caf6c4929c5baaf8edd8be8cac00268e5847",
+      "eval/datasets/coding_memory_v1/oracles/helios-green--unsupported_questions.py": "f78986b8093eab4ecc8c1319d359498d64177db55a4e38cf8d0b32d1e5af4b2a",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--code_relationships.py": "81721c60bd4e3466600442214147ae6641ebc05ae414965f4a09b89cc74cb8d6",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--condition_values.py": "8fbcf116c1f0d480d61b2974e7bef73acef053d45bf0ac3b12e6ea48b017e43f",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--corrections.py": "beae8d6c5828c1f225e5e953236136a217ee48e67cebc82049caf8f1c60cfdcc",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--long_documents.py": "019e7ff3b9efcb461c1c68acc657b2438cc2d63d4b4165c0caa4523c440f12bc",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--multilingual.py": "a48324390ab60686c2b1417f0c049f47601737c55fdf000b696ccc5de260ccab",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--paraphrases.py": "9e2552399b988a6d722ccfaec7cfbea10853164336fadc9e9146dbae788a2d8a",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--poisoning.py": "75eecaa42c302898581d3bef8aee00fa1dec6c3bc968c0014a522196e18c7681",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--scope_boundaries.py": "8bd32a30cd1c2e346375bf2b37ef4908c3feeb67a80ec52ed3108bfe9cbd548e",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--temporal_history.py": "1d1118cb5d438f91bb027acaa3b64f867e93cca7eb0f480bb83073584fafd97a",
+      "eval/datasets/coding_memory_v1/oracles/helios-north--unsupported_questions.py": "02a854bf89085637e366f801d2be6ab26b9e18296f13531485d08c2a64621c7c",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--code_relationships.py": "e32101847ccad5cd18fbc2c667ba4d1b63e3e7f8067dc89de5f485546dfef525",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--condition_values.py": "c8ef59dc9dcfe3aecc990d82fe44f1f93b7adc8c65f1fc38e79b934d351635c6",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--corrections.py": "a3a36bb554a6f4a83ea612bbbe9c0ee4ee1a08071e490a9a909c46d3049bb379",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--long_documents.py": "f9fa707bb28b4d7ea96e3bacfa22f24502b571a76a79defd147fe9d5205963a2",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--multilingual.py": "cfbfe0535e905dd58434bc25d84e7746dbdf1fc50d72d0fa96cc78677eaf18b9",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--paraphrases.py": "1743c8cbf0564d91dfb4db88b694072fdc9bb5a0b9f26f578649af7f539ee393",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--poisoning.py": "02cf390520757473e9d677f5c1f0934ecf50645ad5edcdc64caec23721a5d99e",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--scope_boundaries.py": "5ab003dfc23cb00d0a70195541a780a4b80b1d496728b2b88f7f154310e67a6d",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--temporal_history.py": "209e95f62c39d3f2223ed00a378788e396d04de392324455cd9d19dedb3a87ad",
+      "eval/datasets/coding_memory_v1/oracles/helios-violet--unsupported_questions.py": "a3ff0703297e2f743917e74abeffc0c922a6241318f37d63a49242c6bcc18059",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--code_relationships.py": "4d8543e4c49d59f844830ccee3fcea0643ee17ce43f51863b94a1b4fbc9825ea",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--condition_values.py": "f2efa7fd803df0e10c440d5ec2d98dedf5e02e23a4cedddcde5ea722f4039e40",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--corrections.py": "181c42640cee47db2b5c779bdf8fe2e84103a92459d7f6cb0d9587458e421406",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--long_documents.py": "49337830deb24f9d6b11ba4e01f397c0cf1a40a15524f1ce33354a2c61615072",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--multilingual.py": "f1e4ef8be6bba13457a2da1c3a2082f81bba765f2cf1f07b93eb20edf5e2debe",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--paraphrases.py": "29abfff3b323496fb62e739cdc0be2aada1b7e1467a141cc8d19a1d54c1ab130",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--poisoning.py": "14b7f874c10681ff3829b2659cbe7500250369652d11b26c842e62718093ca0f",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--scope_boundaries.py": "decbdb3cd7ab0c40c0aadb1ecdeef9e2ee2586dd8802b9bb16235f211ce05ee1",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--temporal_history.py": "6e7c2369157234374d3f9633b7e772b4a3bff405d418c6e1336e56c87ebf28de",
+      "eval/datasets/coding_memory_v1/oracles/helios-west--unsupported_questions.py": "379716803a300bbecd3fc8f1661bdac2fcd8a98a2bb18514d8de168bd57fa144",
+      "eval/datasets/coding_memory_v1/oracles/island-green--code_relationships.py": "833962801d594247d5c5644df0e6aee877d452127ea5c0dbc22c81512132ab21",
+      "eval/datasets/coding_memory_v1/oracles/island-green--condition_values.py": "cfbb4ea0a4dd12d69686178ba8246bd08b93743dc5395cd0479984a53655d909",
+      "eval/datasets/coding_memory_v1/oracles/island-green--corrections.py": "4c7ee2538df9988864e24d9b86805d26b64d1a37638b57abdd1761e24c4ab340",
+      "eval/datasets/coding_memory_v1/oracles/island-green--long_documents.py": "f73cd2b884539680c500af9a5c8cc00d1dc9f1d2ef7bda61f6c8253b2bf799ed",
+      "eval/datasets/coding_memory_v1/oracles/island-green--multilingual.py": "e954fa56aa819ef9088c8d6da4abd647b689956c4ff4a7b0b8e31078522f2702",
+      "eval/datasets/coding_memory_v1/oracles/island-green--paraphrases.py": "4cde223eac40d4a2962aa2ace533b8761c5b82784767b0307c884ac5e6ad0576",
+      "eval/datasets/coding_memory_v1/oracles/island-green--poisoning.py": "08725e295848b2c58c9e6d6a0554a2dd4a6506af75039205c444251d11a62acb",
+      "eval/datasets/coding_memory_v1/oracles/island-green--scope_boundaries.py": "257cd579af07491748f5de88d04f8af85056b0448d348e59c7b0cbb28754fb1b",
+      "eval/datasets/coding_memory_v1/oracles/island-green--temporal_history.py": "e93105f0639a83b300a6de3bbae56166eedac2e58122f7e84ce5a40a074db6b6",
+      "eval/datasets/coding_memory_v1/oracles/island-green--unsupported_questions.py": "a707cee90fb3f0cabd0e692399a361f59da0fc4e9e7bbf0cde702e05579f0b3f",
+      "eval/datasets/coding_memory_v1/oracles/island-north--code_relationships.py": "f00e022ce900e4ad0fcec93f2dbf016337a4d83afacbcf739f61f71316723173",
+      "eval/datasets/coding_memory_v1/oracles/island-north--condition_values.py": "c704a03a70253585a67823826dc0a6ebaf6323a8880c00af80c148c150176daf",
+      "eval/datasets/coding_memory_v1/oracles/island-north--corrections.py": "e2cadf6e4f365f94cf0f440758b173da4d14ba12c03a84351e0608f0c60bccc5",
+      "eval/datasets/coding_memory_v1/oracles/island-north--long_documents.py": "300246fd3d85d73b63066d133361bc784ae26b46f4197c5c41ac960eb37f9508",
+      "eval/datasets/coding_memory_v1/oracles/island-north--multilingual.py": "f8aba8e14ed3c420e90e701880ea38e924e1219e3cc3643ba8bde17cb31ddef6",
+      "eval/datasets/coding_memory_v1/oracles/island-north--paraphrases.py": "503ce2c132c666bb67920e90d4a898f5a73f1d66779cd83c1885812f223e30e5",
+      "eval/datasets/coding_memory_v1/oracles/island-north--poisoning.py": "3369d956e5af12bc6be80828c4c6ab03ccf80c79e38dea3162b4e2c09771ff30",
+      "eval/datasets/coding_memory_v1/oracles/island-north--scope_boundaries.py": "9b4f6186f71713175f1eb5aacb0b6258c746b2297ca7c692f54bf5feabd5d261",
+      "eval/datasets/coding_memory_v1/oracles/island-north--temporal_history.py": "7c22b0edbf8edb7a511a581ffe6f1ce14454ef3feb527eca90d1386ce00b2c6b",
+      "eval/datasets/coding_memory_v1/oracles/island-north--unsupported_questions.py": "c1e5d526b0c6b88394f19a8b8edca7dae1db718b24be2d57374eb3769bbd1f24",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--code_relationships.py": "9672d608ea0c8623ff1fe760f943173b2fdac5dc4ea4b7ae0dba33436d860254",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--condition_values.py": "cfea91adcc9b3f9eb28cc24cf310e10b436f81cff51297f161b9a3b59a21f62c",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--corrections.py": "075d48a2dfd91af8328982fe475ec915c00b75db38819aff3b4c2343147e2bfc",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--long_documents.py": "85cc789277e59925b36ea3bd82e23f989e79fb0be2e55083e2656e518641dd3c",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--multilingual.py": "84615b70eb74eb2180dd8a89d8d34c11e904030bfaa26c57e2e6c968daf64d29",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--paraphrases.py": "5244d32ffc4127d519e2f5a875ffaecf7bc51eaa1426d2aacbc42490cf291d22",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--poisoning.py": "9bde478876ea0be60555d5bd26d3790e4f305327ece10bf6c258bc564354fa1d",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--scope_boundaries.py": "8e8b0a64342963b4dbc000578a72c0e0801fc1ca4af140f09b55d4cdb03b1274",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--temporal_history.py": "3e187ce259c7f57f6dba4a28c3ecdf31fbe6458f7d908b22cb8b5ce8325437ae",
+      "eval/datasets/coding_memory_v1/oracles/island-violet--unsupported_questions.py": "0e60f29a47953c5d434c159eece26bbb03cc837842c493111b34310f9cff4693",
+      "eval/datasets/coding_memory_v1/oracles/island-west--code_relationships.py": "c19c42978fa5f9c6e1f41886eb1cc0fdb7e12304ba58b160b4cbe1975640acfe",
+      "eval/datasets/coding_memory_v1/oracles/island-west--condition_values.py": "07c4c591e08f5248f3016dc16cecfea7dd75bebff1a61599f258938d7031043d",
+      "eval/datasets/coding_memory_v1/oracles/island-west--corrections.py": "a7d93dfb579ec4f58cf2f6d29a6d0ab7dbf1a17f6ae49b98902a5ea22525e649",
+      "eval/datasets/coding_memory_v1/oracles/island-west--long_documents.py": "20a50dd63e04ce751115fca671b9da7ebbf240e26f39d494583cb405a03b750c",
+      "eval/datasets/coding_memory_v1/oracles/island-west--multilingual.py": "65d82c4d7968e0e597509c692015bdac0b92841c726d87560d9caa32429176f4",
+      "eval/datasets/coding_memory_v1/oracles/island-west--paraphrases.py": "feb7eb2e8592162d7d1f433610cb02ba04cd9797191d65a9f0e5bc4f4711c4ed",
+      "eval/datasets/coding_memory_v1/oracles/island-west--poisoning.py": "3d7c2c6a7f247f3e8158d5ba007bbbdf027a74e9a2c52f52953b3ccf2c21f17f",
+      "eval/datasets/coding_memory_v1/oracles/island-west--scope_boundaries.py": "ff0f36139f6da5428b9538d108aded522e62ca803035ebef78e11255cf55e08b",
+      "eval/datasets/coding_memory_v1/oracles/island-west--temporal_history.py": "42cb1c552ce01308b47d526c6e6993fb3270239b392cfa9f5e42b8e0fcfb3f82",
+      "eval/datasets/coding_memory_v1/oracles/island-west--unsupported_questions.py": "911b4257380640d35d6e2fc5292e235eedc113f5e71d8e71e8ccab7c72d4f290",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--code_relationships.py": "373395d3b70f64f8102609d27ce10c4aeb937ac73988c2ce2be1e283df94ef82",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--condition_values.py": "f04794a96b06d537550227ec308b1f02405cdab42d7d3ae4db4afd2c25bee8cd",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--corrections.py": "5a354a8c8efdbc498d25ffbf6095fee7b3d7d638134b452c7c9ecb186b4e1bc7",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--long_documents.py": "8610157668d6a90c794a956f6f0b432f03e3559238599ad1cb412f6f1a2f7e46",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--multilingual.py": "dcb99335fa18b008197532809ff7127be2cda600848e10c8bfe4677bd896f90e",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--paraphrases.py": "7a4cb1bbe3de2e6fe6a33b1f78829f4aeb21d21c2e8d4d3399d3d98958ba0909",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--poisoning.py": "ba73c2c6f04590538e16c50be527da60f5949781bc8833a3c18a7c597146eb10",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--scope_boundaries.py": "9d09c0851a3906b6281cb1c5811714224161e27a1aa46edd81c5659e7f93cd3d",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--temporal_history.py": "fd05595a452952dca2d0089f5701a60145a3b5705b78a5ff2f8f9f13fbf1c259",
+      "eval/datasets/coding_memory_v1/oracles/juniper-green--unsupported_questions.py": "f58bfcb89db799dc1578fc8791b49e97e7f22b30e720aeaf661f0ad2e6a9660c",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--code_relationships.py": "a84f02bd3c2b9c367248dae8aa3580d83de6a1beb6fe464553eb8a2bfb172b75",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--condition_values.py": "d70311ae339556f18240f824d0f0bd0024060c2698fcca8fe7cb540e8a8bc727",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--corrections.py": "fa290629339007fdd4230a76d49fa294a218c5f0cf6b90c3074678b0f16c539a",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--long_documents.py": "e30025d68ae3b48b566bf3fb2aea5e3603f5f7ab658da8fcb2256d3b1964c85a",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--multilingual.py": "b8bb0199c4acfe71df8d4e7df75bdd37e038cc72aa82bc6df10715819aeb3686",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--paraphrases.py": "aabf70509d3b0602d43c9590f04fa3ad1370a40c266d20f64a5ece15d4c79a51",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--poisoning.py": "ebfb9d7bf3c50eed8f44b73e391496ef377942de389b6feb64c7a1c0f9646444",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--scope_boundaries.py": "06c2c9d57ade79139c9b0d20568703477bb9e3a934f2f8900ad717ef157e5844",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--temporal_history.py": "0d97ba6d7a5d7741bf248b599ed18ae81b1c0053ad53cbc64934f31e9c3461aa",
+      "eval/datasets/coding_memory_v1/oracles/juniper-north--unsupported_questions.py": "526648ba7a4edc21bc2eb589c1e5c98a20fb07aa692687de4c3845e559be8096",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--code_relationships.py": "c73fd24d0adbeda6c7afeb15ab07296c0438402893e8d442af26865106d6e8ea",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--condition_values.py": "4aadae570ef84f976d49ba1fc92574ef55630b1c3017e90dbec1f85e6fb74c4a",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--corrections.py": "07236b2a88df73c8d0f6afbe7d972fdc18f8c835a852f5c20748a369c77d82e2",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--long_documents.py": "54d3201b621b168ce03963c423942f142cb403f9d90234f063ff33b7add4d2dc",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--multilingual.py": "e0cc26d743cbea8e98261895474879d078fd53941c075606bfc6e52ee098db93",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--paraphrases.py": "a1f836316408052cab1253b56b5caa6b1432fe6eeaabbb5872da97ec9bde633a",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--poisoning.py": "bc09271eadf77f1b6c03fff20ca9c0f0a42a99d1c5600e6b7843f0a0d549ed5d",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--scope_boundaries.py": "17a7258bed9efe1c86a05756c5b5d17926fd72f01de4b2addd5d2fb4550f4da5",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--temporal_history.py": "8bda8599d861857204c48b55729607c8cb0cb3ae2701eb18fb600d398468cafe",
+      "eval/datasets/coding_memory_v1/oracles/juniper-violet--unsupported_questions.py": "10cdbb013f78f0e54c31a6e76f03d8d15a6063fd7971a2d803a390890c036ad2",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--code_relationships.py": "f0a682d413b3d8418c664db2775de4eef35240c508cc71ca6bbc055cd0c8dbe6",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--condition_values.py": "200a4b78f201e992ac10112a194c97b88841dc5930e3e7de9bfc076bf4c69fa7",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--corrections.py": "41ea9b5a5f40d8703343f4570593c3f27905e5ff70fae57bdbdb5fcccc585d22",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--long_documents.py": "7d8cdd01c5d90ad62e9da93a99febead683e3f01c5ca37315382a2fb0f512d76",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--multilingual.py": "1815adc5946bf9e7dba16786d8c29f9466537b7a43b1c392f927b61c56da54ee",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--paraphrases.py": "5d0110bc2098d2143303476fb5c5714086d0278b848110c63aa626e0b88311cc",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--poisoning.py": "4e16d9de9931cffc6915805b4fc375dad3ffb7fad17eb893205ce6d07102bcb3",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--scope_boundaries.py": "6c5d875184c890a922ee18ac423598fdcece109a91e9e62d5a7ccc82d2eaaa70",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--temporal_history.py": "3404fdbb5cc4693333d48d27da928531279d148ffe1cdadbdd741dfc1a8d38d3",
+      "eval/datasets/coding_memory_v1/oracles/juniper-west--unsupported_questions.py": "b85a4cf14f9596cd14b480acd323772fc91084ad1413fa27435bdb7ffe5baa6b",
+      "eval/datasets/longdoc.jsonl": "7f5ade95e1f283d0db8cf78e53ed8995d3534f847e616d2c0005fd8da37ac790",
+      "eval/desktop_memory.py": "65a3b5fcd248948c209baa115b275a6db40b386be5f0828bf9ca611787fa02a6",
+      "eval/engine_capacity.py": "1940da1c3a435d81c7b7a1a689e966c23b92e4f94af115b45813dd30e2c04eec",
+      "eval/evidence_contracts.py": "03969fdf01e78135c66e698d3f523e5312ccca3737dd3036b37a2c6676ba4ea2",
+      "eval/external.py": "98500a97c18152b1b86a270062033c48176224d7468ac0f703ddc7de862a30e2",
+      "eval/external_checkpoints.py": "484e298039bfa04eef86bd7145428c312aaeaf059f5bdf8da7ae29d1150008d7",
+      "eval/extractor_quality.py": "50820fe7f821d111e17e4e77a3d1159e7d6979d110b052c4f254a5b309c2652a",
+      "eval/fts_insert_scaling.py": "6088997e0f85d430fafb74509e24a960fbd59c06c8b2839285942b97d2116724",
+      "eval/graph_every_bench.py": "79da573c5edf315f71bfab412d3ea283b8da45d1fdabc78ddd19302ead09e4f0",
+      "eval/graph_traversal.py": "b094f75c3a1d75ba3cf19e372187d692d3c595a1d9bde19bbe95ae0c79a5175f",
+      "eval/grounded.py": "053d5193b716a2c3e507fcd44057d392de910a4442b46bd7cc1f30ac0ba68541",
+      "eval/handoff_quality.py": "7daf635510764e236f48ca7e2537a85d8ebc1ad995513144329c1f0236405937",
+      "eval/harness.py": "8c96c26a121dfc2d9ea051a05861af8951c93a732dba9cb13de0de178414b016",
+      "eval/hosted_evidence.py": "7946cd8c1e3aa291268271b2aa11210d5f09c9b05ba635aa0b64bef07bdcee45",
+      "eval/hosted_ledger.py": "a53036d12ff671371c148910a816fb20c7e7f3346250a303722352f47b06c476",
+      "eval/hosted_luna.py": "4dbf02a65eec38bcde92d82952a0b372abbac1f68378d11a04528f4a31a835dc",
+      "eval/jev_recall_quality.py": "3c31080767c2bc0301f1085c837eaa60ac6e1f5ae8eeb6ff908e573a630510cd",
+      "eval/local_benchmark_queue.py": "d87ace3cf9ed59d65e57917e5387ff226c1b8a4abef8b98719c5de3aa1b8dddc",
+      "eval/local_capacity_campaign.py": "ab4935263f9d24c4e38bd4f16164b4c4c07eff91c695809b6fc75299d4f03d62",
+      "eval/longmemeval_v2.py": "defb4d47f453aa4615a8f101b82df3fadf64f0f9eae0ce1021d86d3750dad437",
+      "eval/longmemeval_v2_evidence.py": "8486bd4dcfdd8b1f7a14c32fe4f427c980ccdcc3aa2eb018d7dfc40305412eff",
+      "eval/longmemeval_v2_matrix.py": "ca085cd59481813cce5dbdfbc94f40f67173ac3a1bc3dce6f6d3e09eb7b08153",
+      "eval/metrics.py": "16857e2cf6ed339cb57a26c9bfa1879444b4d279bd972e5a9fa644ed1308afe0",
+      "eval/native_coverage_scaling.py": "1df274ae8f0a8266282fd5b530167aa749ab67024349bf97c6c0a5a4987bfa77",
+      "eval/performance.py": "dccc55c26dc396f9fee98defd152900cf8aabeb5d6198bc711e0eb8f472ecc57",
+      "eval/performance_engine.py": "3d37cf0a5989c8fa6e8b6ab7ae0b2e0d5410a8b922d2f3130c1a7794d93dcbb1",
+      "eval/planned_recall.py": "f9a87291ecb181045b98ca65fe55db820bf7cee4ae4f4d087ca3458afdd7837e",
+      "eval/proactive_ranking.py": "8610541f1d547f9c0eb46d078dbcaa670c0a97157acc37f96ec08b482cb7a6ab",
+      "eval/productivity.py": "6d4644ebdc44472aeb3879963774fab276bfa269b781139c46ded48774a22717",
+      "eval/public_readiness.py": "5ce8a18d0bfe09e75e88548a589b8fc6d2cbf04c0f8cd1ce51cd9519136a2751",
+      "eval/redteam_poisoning.py": "fce120cc3adf2ee966b59cd3ea7f20d242a0af49b52492143543130fe14c0cc8",
+      "eval/reinforcement.py": "72ed766775a2658eaa728afec51c0ac22d97a90e813111954df66a6ec50f2bef",
+      "eval/repair_discovery.py": "db05496fbbcb0df86c5cdc2f0c85fb6b6605b0cace6cb44ae2add10b72784b5f",
+      "eval/resolver_reworded_corrections.py": "a9054778a37b2175b46f04b674b4779e358931eee5d2ae52bbc5f953d234fb9e",
+      "eval/resource_hierarchy.py": "5ab6c989bb143c4386749c45a33c190447e829c1b5657e8c0aca30f34bd69461",
+      "eval/rework_statistics.py": "e12c14288797c5cf2dd93d51f606244287bc2f4ff8bd401f1d1b072efd1f9529",
+      "eval/run_longmemeval_v2.py": "866863d9f8f7ce8f7c3c36741ab324faa5fae417827f907c655eace38de0f5ac",
+      "eval/spec_crawl.py": "da3b079ab5674ce1004b0dafcfd471da9897c951a03456ba704b720b719f3295",
+      "eval/task_pairs.py": "fddc54804e8837ec0731813297fb55825458317f898e29176e16f3f5a2f527fd",
+      "eval/user_journeys.py": "a1c8436d4a6871baff21f9aa4f6ac1545def60d946cd3b1454c3d9cd8661a049",
+      "eval/vector_scale.py": "3f9c327d9eca1a857512ddc208e972933be1a7d4fa7fa0017aca0cbf8fe7bb6d",
+      "eval/vector_scale_storage.py": "24040fd1b96b9f9cd43ea37b0b37ea118a02bd096aff77fc67ff8b0df769b1dc",
+      "eval/vector_scan_plan.py": "34fba3d029bfc78134e8c9c450b019ff56c3bdcbeb921400888077cb44e9b848",
+      "scripts/export_offline_evidence.py": "4e10c2b3d5f6a2024a7f95f7b87ce47ec2cb4ef31c55611b2e5cf35502ebc0ba"
+    }
+  }
+}
diff --git a/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json.sha256 b/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json.sha256
new file mode 100644
index 00000000..80707740
--- /dev/null
+++ b/docs/benchmark-evidence/offline-fixtures-release-1.7.12-20261102.json.sha256
@@ -0,0 +1 @@
+025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660  offline-fixtures-release-1.7.12-20261102.json
diff --git a/docs/images/context-efficiency.png b/docs/images/context-efficiency.png
index 8a12db21860f3705a92a9f17e895b1beb7743e00..a041b6868fed93b18b4632cb602f944d8dc82e17 100644
GIT binary patch
delta 153
zcmWN_yAi@L3;@uA1z3O`BwLo8Iw@E~)@Kze?x10gP*Jl<N{)sVNcrBn9oFq|n-?ez
zdu2dtTDn$o&8ZevU<8ChG;GqEQ;H9a8tjyvIaJe_;rc$#_seNPh(eWwyt}aVFd@P8
fHWHBud!V`H4iEril0n(_6!AbF^!h%YpY!hzu$3=U

delta 153
zcmWN}s}%x43`SwGigRcIkIYWy70n82!2L5xT0sJxES0Rnuf)*;<F2^pTlZ<*r{`s<
z>VaGdQbtfA^pJC?HcLyexmix!wE)r!i)ak7n>tx#0nNw9=kU6pmTEy81WM-Ky^@4P
htcfGy*azQI)*K7xfdUla4(o^_0mAETJHNlz-ycn`FtY#v

diff --git a/docs/images/context-efficiency.svg b/docs/images/context-efficiency.svg
index b5dbee06..0ebae922 100644
--- a/docs/images/context-efficiency.svg
+++ b/docs/images/context-efficiency.svg
@@ -1,6 +1,6 @@
 <svg xmlns="http://www.w3.org/2000/svg" width="1103" height="670" viewBox="0 0 1103 670" role="img" aria-labelledby="title desc">
 <title id="title">Offline context, retrieval, and grounded benchmark results</title>
-<desc id="desc">Artifact-driven offline benchmark report with context efficiency, retrieval quality, and grounded behavior reported separately. Structure-aware chunking reports 740.3 to 214.3 retrieved tokens per question. The JSON-shape payload proxy reports 24,590 full versus 11,138 compact tokens; MCP transport was not measured; provider billing was not measured. Retrieved candidate quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Packed context quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Grounded checks score 5 of 5 answerable queries grounded and 6 of 6 abstention queries rejected, including 1 of 1 quarantined-evidence checks. Decision accuracy is 1.000 across 11 decisions. Source artifact SHA-256 8df20fd0a97f20070ac26628e19b5ae1be653cd7aa9c7399d424cedf0e839a01.</desc>
+<desc id="desc">Artifact-driven offline benchmark report with context efficiency, retrieval quality, and grounded behavior reported separately. Structure-aware chunking reports 740.3 to 214.3 retrieved tokens per question. The JSON-shape payload proxy reports 24,590 full versus 11,138 compact tokens; MCP transport was not measured; provider billing was not measured. Retrieved candidate quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Packed context quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Grounded checks score 5 of 5 answerable queries grounded and 6 of 6 abstention queries rejected, including 1 of 1 quarantined-evidence checks. Decision accuracy is 1.000 across 11 decisions. Source artifact SHA-256 025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660.</desc>
 <style>text{font-family:Consolas,monospace;fill:#b9c8dc} .heading{font-family:Segoe UI,sans-serif;font-weight:700;fill:#f2f5f9} .green{fill:#00c896}.muted{fill:#7589a7}</style>
 <rect x="3" y="2" width="1094" height="664" fill="#0e1114" stroke="#252c36"/>
 <rect x="22" y="20" width="224" height="21" fill="#1c222b" stroke="#303a47"/>
@@ -65,6 +65,6 @@
 <text x="750" y="541" font-size="13" class="heading" text-anchor="start">Quarantined-evidence probe</text>
 <text x="750" y="575" font-size="21" class="green" text-anchor="start">1 / 1 abstained</text>
 <text x="22" y="610" font-size="12.1" class="muted" text-anchor="start">Decision accuracy 1.000 (11 / 11); the quarantine probe is included in the abstention total.</text>
-<text x="22" y="651" font-size="12.2" class="muted" text-anchor="start">SOURCE SHA-256  8df20fd0a97f</text>
+<text x="22" y="651" font-size="12.2" class="muted" text-anchor="start">SOURCE SHA-256  025183601c5a</text>
 <text x="1080" y="651" font-size="12.2" class="muted" text-anchor="end">JSON proxy only; MCP transport not measured; provider billing not measured.</text>
 </svg>
diff --git a/docs/images/evidence-backed-agent-examples.png b/docs/images/evidence-backed-agent-examples.png
index 69f12ff7eb9f1084a815ea0e22e017f5ed0455aa..479118856da0d8576587ca3244012a6a83b6fe05 100644
GIT binary patch
delta 165
zcmV~$yAi@L3;@vMQ&46BN-7%3vSq7I7Evr~1bT`b6?ZTU1293#tl*Lnc<;9jzioJp
z6NH3?7_cS{MJb!QP+$c{KnO9;Rg_#j+l-AGTlB)*RJ}68^E-_1$9c*rnOdw)QG^mu
uEsT~aHX{;oCaFnW-BKu?GZaoG#$ZM>68i13uJ^w5-O~3<KYaS}bo~QNYBS9M

delta 165
zcmWN}s}TY*5CG8OBVYzW15|+7d^VfaTqB$8rVqpo5-0{w6U<p;<OvGk+*5C!j`MVU
zT!yU8LsJl@1wbIxr{uFaE-2=TB@9(bgewJRjXqY>29^U0xWoOkf8I_*D<+LhFms8K
wGpUqZYVZjJlSA}DK$ill3z^ZZX%dQrAt_pWy}!R}ANy+T>#=WMeY-pV0sLJyTmS$7

diff --git a/docs/images/evidence-backed-agent-examples.svg b/docs/images/evidence-backed-agent-examples.svg
index 4ba7cbd0..5631c9c1 100644
--- a/docs/images/evidence-backed-agent-examples.svg
+++ b/docs/images/evidence-backed-agent-examples.svg
@@ -1,6 +1,6 @@
 <svg xmlns="http://www.w3.org/2000/svg" width="1693" height="929" viewBox="0 0 1693 929" role="img" aria-labelledby="title desc">
   <title id="title">Three evidence-backed Engraphis agent behaviors</title>
-  <desc id="desc">A three-card summary of deterministic offline fixtures. Focused context returns 740.3 to 214.3 tokens while retaining Recall at 5 of 1.000. A grounded answer returns support for 5/5 answerable questions. An unsupported question safely abstains for 6/6 off-topic questions. Reproduce with eval.chunking_eval and eval.grounded. Exact commands and config digests are registered in BENCHMARKS.md. Public-safe artifact SHA-256: 8df20fd0a97f20070ac26628e19b5ae1be653cd7aa9c7399d424cedf0e839a01.</desc>
+  <desc id="desc">A three-card summary of deterministic offline fixtures. Focused context returns 740.3 to 214.3 tokens while retaining Recall at 5 of 1.000. A grounded answer returns support for 5/5 answerable questions. An unsupported question safely abstains for 6/6 off-topic questions. Reproduce with eval.chunking_eval and eval.grounded. Exact commands and config digests are registered in BENCHMARKS.md. Public-safe artifact SHA-256: 025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660.</desc>
   <defs>
     <linearGradient id="page" x1="0" y1="0" x2="1" y2="1"><stop offset="0" stop-color="#f8fbff"/><stop offset="1" stop-color="#eef4fb"/></linearGradient>
     <filter id="shadow" x="-10%" y="-10%" width="120%" height="130%"><feDropShadow dx="0" dy="5" stdDeviation="8" flood-opacity=".12"/></filter>
@@ -47,5 +47,5 @@
   </g>
   <line x1="70" y1="832" x2="1623" y2="832" stroke="#ced8e7" stroke-width="2"/>
   <text x="846" y="875" text-anchor="middle" font-family="Inter, Arial, sans-serif" font-size="24" font-weight="600" fill="#53627b">Reproduce: eval.chunking_eval + eval.grounded</text>
-  <text x="846" y="910" text-anchor="middle" font-family="ui-monospace, monospace" font-size="15" font-weight="600" fill="#53627b">SHA256 8df20fd0a97f20070ac26628e19b5ae1be653cd7aa9c7399d424cedf0e839a01</text>
+  <text x="846" y="910" text-anchor="middle" font-family="ui-monospace, monospace" font-size="15" font-weight="600" fill="#53627b">SHA256 025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660</text>
 </svg>
diff --git a/eval/chunking_eval.py b/eval/chunking_eval.py
index d0c693ca..e2107d00 100644
--- a/eval/chunking_eval.py
+++ b/eval/chunking_eval.py
@@ -57,7 +57,8 @@ def run_eval(cases: list[dict], *, mode: str, k: int = 5,
         raise TypeError("chunk_extractor must be a ChunkingExtractor")
     count_tokens = selected_chunker.count_tokens
     svc = MemoryService.create(":memory:", embed_model=embed_model, embed_dim=embed_dim,
-                               extractor=("chunk" if mode == "chunked" else "none"))
+                               extractor=("chunk" if mode == "chunked" else "none"),
+                               retention_supervisor="none")
     if mode == "chunked":
         svc.engine.extractor = selected_chunker
     # The checked-in fixture is trusted test data. Raw service ingest correctly marks
diff --git a/tests/test_benchmark_evidence.py b/tests/test_benchmark_evidence.py
index b731002f..bede7085 100644
--- a/tests/test_benchmark_evidence.py
+++ b/tests/test_benchmark_evidence.py
@@ -34,8 +34,8 @@
 
 
 ROOT = Path(__file__).resolve().parents[1]
-PUBLIC_OFFLINE_ARTIFACT = "offline-fixtures-automatic-browser-access-20261101.json"
-PUBLIC_OFFLINE_SHA = "8df20fd0a97f20070ac26628e19b5ae1be653cd7aa9c7399d424cedf0e839a01"
+PUBLIC_OFFLINE_ARTIFACT = "offline-fixtures-release-1.7.12-20261102.json"
+PUBLIC_OFFLINE_SHA = "025183601c5a28a37daf9326a061010244bc9a3f9f7db1e3e6d4f866eaafc660"
 
 
 @pytest.fixture(scope="module")