> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [rounds/review-off-hard-1/README.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/README.md)
- [results/run-records/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/index.json)
- [rounds/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/index.json)
- [results/source-crosswalk/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/source-crosswalk/index.json)
- [rounds/STATUS.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/STATUS.md)
- [reproduce/round-inventory.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/reproduce/round-inventory.json)

# Does the default builder need review on harder tasks?

**Round ID:** review-off-hard-1  
**Status:** DESCRIPTIVE

> Reviewed status from rounds/STATUS.md: DESCRIPTIVE.

> Round README and results text are source material. Numeric values not tied to a claim ledger record remain source-reported.

Exploratory Kogen Lab screen on four development-task IDs, with two repetitions each. A rescue means review turned a failing first-green tree into a correct submission. The round is approximate: Lab verified the code in the builder's workspace, not in a clean copy of the candidate as Kogen now does.

## Question and scope

Would the default review step prevent incorrect submissions on this task set? The review-enabled arm used GPT-6.1 Sol as builder at medium effort and reviewer-fixer at high effort. The review-disabled arm used the same builder settings and submitted its first green tree without review. Both arms ran two repetitions on four task IDs: vm-go, vm-ex, cron-go, and cron-ex. Task specifications, hidden-test material, and reference solutions remain private.

## Results

First green means the first build that passed the workflow's checks and was ready for review or submission. A correct submission passed the complete evaluation represented in its export. Five review-enabled attempts had reviewer edits; model-free grades show their trees were correct before review. Three other review-enabled attempts were submitted unchanged. Each review-disabled submission was its first green tree. The exported public ID states are preserved per attempt in the bundles.

| Setting | Correct submissions | Wrong submissions | Wrong at first green | Reviewer edits | Total input | Reviewer input | Sum of recorded stage times |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| Review enabled (default) | 8 of 8 | 0 | 0 of 8 | 5, all on correct code | 2.11M | 1.13M | 3,497 s |
| Review disabled | 8 of 8 | 0 | 0 of 8 | 0 | 1.01M | 0 | 2,588 s |

| Task ID | Review enabled | Review disabled |
| --- | --- | --- |
| vm-go | 2 of 2 correct | 2 of 2 correct |
| vm-ex | 2 of 2 correct | 2 of 2 correct |
| cron-go | 2 of 2 correct | 2 of 2 correct |
| cron-ex | 2 of 2 correct | 2 of 2 correct |

One review-disabled attempt on vm-ex used one repair; the other 15 attempts used none. Builder stops: 0. Builder refusals: 0.

## Fixed rule and decision

The fixed rule counted the task set as informative only if at least 4 of 16 first-green builds were wrong. If that threshold were met, review would be needed for the default builder if it rescued at least 2 wrong trees or if review-disabled produced at least 2 more wrong submissions. Otherwise, review-disabled would be a candidate for a fresh confirmation. Here, 0 of 16 first-green builds were wrong, below the threshold. The fixed decision is **NOT INFORMATIVE**: the tasks were still too easy, so the round does not establish whether review should be disabled.

## Limits

This was a descriptive screen on development tasks. With no wrong first-green build, the run does not measure whether review fixes errors from the default builder. The round does not establish whether review can be skipped on other work. Task specifications, hidden tests, and references are withheld; only task IDs and the public per-test outcomes in the bundles are published.

## Required reproduction metadata

- [Run records](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/records.jsonl) contains one Standard 1.2 record per scored attempt (16). [Measured fields](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/MEASURED.md), [declared gaps](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/MISSING.md), and [missing-field data](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/MISSING-DECLARED.json) describe record coverage.
- [Pre-review grades](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/PRE-REVIEW-GRADES.json) contains correctness classifications for the five edited attempts in the review-enabled arm; hidden-test counts are not included.
- [Public bundles](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/bundles/) contain the frozen settings, task IDs, and public per-test outcome IDs exactly as exported. Task files, hidden tests, references, transcripts, and candidate code are withheld.

Re-run on the real Kogen build: [review-off-hard-1-kogen](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1-kogen/README.md).

## Metadata

Round date: 2026-10-21
Label: DESCRIPTIVE
Publication badge: DESCRIPTIVE; KEPT FOR AUDIT
Recomputation status: OBSERVED SOURCE ONLY
Why not VALID: DESCRIPTIVE_ONLY, PROTOCOL_DEVIATION, INCOMPLETE_CAPTURE — exploratory development screen, approximate execution, no official grades, and missing Standard capture fields declared below.
STATUS: **DESCRIPTIVE**

## Execution record

- Lab build: 3bf295ef.
- Kogen commit: b45ba32bacf26e2b17cb0bb81015ba56d27a4b0b.
- Harness commit: not recorded as a public Git commit.
- Purpose: development.
- Model and effort: builder GPT-6.1 Sol at medium effort; reviewer-fixer GPT-6.1 Sol at high effort. The review-disabled arm used the same builder setting.
- Task IDs: vm-go, vm-ex, cron-go, cron-ex.
- Attempts: 16 started and 16 scored; builder stops: 0; builder refusals: 0.
- Input: 3.12M tokens against an 8M cap.
- Review-enabled arm: 2.11M total input, including 1.13M reviewer input; sum of recorded stage times: 3,497 s.
- Review-disabled arm: 1.01M total input, 0 reviewer input; sum of recorded stage times: 2,588 s.
- Command: the experiment was run and exported in Kogen Lab before publication.
- Raw records: [run records](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/records.jsonl), [pre-review grades](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/PRE-REVIEW-GRADES.json), and the public [bundle](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/review-off-hard-1/bundles/).

## What's missing and why
- `circumstances.cap_end` (16 missing): The Lab export does not carry this Standard field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (`m08`).
- `circumstances.cap_start` (16 missing): The Lab export does not carry this Standard field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (`m08`).
- `circumstances.concurrent_cells_end` (16 missing): The Lab export does not carry this Standard field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.concurrent_cells_start` (16 missing): The Lab export does not carry this Standard field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.dispatcher_id` (16 missing): The Lab export does not carry this Standard field. Exact dispatcher revision is not present in the public receipt extract. Reason: Exact dispatcher revision is not present in the public receipt extract (`m63`).
- `circumstances.incidents` (16 missing): The Lab export does not carry this Standard field. Per-cell incident receipt was not captured. Reason: Per-cell incident receipt was not captured (`m78`).
- `circumstances.load1_end` (16 missing): The Lab export does not carry this Standard field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (`m65`).
- `circumstances.load1_start` (16 missing): The Lab export does not carry this Standard field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (`m65`).
- `circumstances.load_samples` (16 missing): The Lab export does not carry this Standard field. Timestamped host-wide load samples were not captured. Reason: Timestamped host-wide load samples were not captured (`m93`).
- `circumstances.queue` (16 missing): The Lab export does not carry this Standard field. Queue receipt was not captured. Reason: Queue receipt was not captured (`m91`).
- `cost.accounting` (16 missing): The Lab export does not carry this Standard field. Per-cell cost and pricing inputs are not present in the public round data. Reason: Per-cell cost and pricing inputs are not present in the public round data (`m70`).
- `cost.calculator_version` (16 missing): The Lab export does not carry this Standard field. Cost calculator version not recorded. Reason: Cost calculator version not recorded (`m61`).
- `cost.long_context_reconciled` (16 missing): The Lab export does not carry this Standard field. Boolean receipt not recorded. Reason: Boolean receipt not recorded (`m07`).
- `cost.price_table_version` (16 missing): The Lab export does not carry this Standard field. Price table version not recorded. Reason: Price table version not recorded (`m89`).
- `cost.usd` (16 missing): The Lab export does not carry this Standard field. Per-cell cost and pricing inputs are not present in the public round data. Reason: Per-cell cost and pricing inputs are not present in the public round data (`m70`).
- `effort.effective` (16 missing): The Lab export does not carry this Standard field. Per-cell effective-effort receipt not published. Reason: Per-cell effective-effort receipt not published (`m73`).
- `effort.requested` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `effort.runner_requested` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `environment.account_class` (16 missing): The Lab export does not carry this Standard field. No owner-approved class-only account receipt is available for the cell. Reason: No owner-approved class-only account receipt is available for the cell (`m100`).
- `environment.network.allowlist_hosts` (16 missing): The Lab export does not carry this Standard field. Per-cell network allowlist not present in the public round data. Reason: Per-cell network allowlist not present in the public round data (`m79`).
- `environment.network.profile` (16 missing): The Lab export does not carry this Standard field. Per-cell network profile not present in the public round data. Reason: Per-cell network profile not present in the public round data (`m80`).
- `environment.toolchains.erlang` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.other_inventory` (16 missing): The Lab export does not carry this Standard field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `environment.toolchains.ruby` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.rust` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `grade.grader` (16 missing): The Lab export does not carry this Standard field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (`m77`).
- `grade.timestamp` (16 missing): The Lab export does not carry this Standard field. No official grade in the public snapshot. Reason: No official grade in the public snapshot (`m32`).
- `host.id` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `itt.class` (16 missing): The Lab export does not carry this Standard field. No evidence-backed ITT classification. Reason: No evidence-backed ITT classification (`m28`).
- `itt.cohort` (16 missing): The Lab export does not carry this Standard field. No evidence-backed ITT classification. Reason: No evidence-backed ITT classification (`m28`).
- `outcome` (16 missing): The Lab export does not carry this Standard field. Not available for ungraded delivery. Reason: Not available for ungraded delivery (`m38`).
- `provenance.ledger_sha256` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `sandbox.egress_allow` (16 missing): The Lab export does not carry this Standard field. Per-cell egress allowlist is not present in the public round data. Reason: Per-cell egress allowlist is not present in the public round data (`m75`).
- `sandbox.egress_profile` (16 missing): The Lab export does not carry this Standard field. Per-cell egress profile is not present in the public round data. Reason: Per-cell egress profile is not present in the public round data (`m76`).
- `sandbox.profile` (16 missing): The Lab export does not carry this Standard field. Per-cell sandbox profile is not present in the public round data. Reason: Per-cell sandbox profile is not present in the public round data (`m87`).
- `sandbox.profile_sha256` (16 missing): The Lab export does not carry this Standard field. Per-cell sandbox profile fingerprint is not present in the public round data. Reason: Per-cell sandbox profile fingerprint is not present in the public round data (`m86`).
- `setup.adapter_harness_sha` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `setup.deps_source` (16 missing): The Lab export does not carry this Standard field. Per-cell dependency source is not recorded. Reason: Per-cell dependency source is not recorded (`m71`).
- `setup.sandbox_mode` (16 missing): The Lab export does not carry this Standard field. Per-cell sandbox mode is not present in the public round data. Reason: Per-cell sandbox mode is not present in the public round data (`m85`).
- `setup.sandbox_profile_sha256` (16 missing): The Lab export does not carry this Standard field. Per-cell sandbox fingerprint is not present in the public round data. Reason: Per-cell sandbox fingerprint is not present in the public round data (`m84`).
- `setup.task_base.hash` (16 missing): The Lab export does not carry this Standard field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (`m42`).
- `setup.task_base.kind` (16 missing): The Lab export does not carry this Standard field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (`m43`).
- `task.base_repo` (16 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (`m39`).
- `task.base_revision.hash` (16 missing): The Lab export does not carry this Standard field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (`m42`).
- `task.base_revision.kind` (16 missing): The Lab export does not carry this Standard field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (`m43`).
- `timestamps.phases.develop.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.develop.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.gate.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.gate.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.grade.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.grade.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.plan.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.plan.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.review.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.review.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.setup.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.setup.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.shape.end_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timestamps.phases.shape.start_utc` (16 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (`m88`).
- `timing.phases_s.gate` (16 missing): The Lab export does not carry this Standard field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (`m45`).
- `timing.phases_s.setup` (16 missing): The Lab export does not carry this Standard field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (`m45`).
- `timing.timeout_cap_s` (16 missing): The Lab export does not carry this Standard field. Timeout receipt unavailable. Reason: Timeout receipt unavailable (`m53`).
- `tools.grader` (16 missing): The Lab export does not carry this Standard field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (`m77`).
- `tools.runner` (16 missing): The Lab export does not carry this Standard field. Per-cell runner version not recorded in the public round data. Reason: Per-cell runner version not recorded in the public round data (`m83`).
- `tools.toolchains.erlang` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.other_inventory` (16 missing): The Lab export does not carry this Standard field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `tools.toolchains.ruby` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.rust` (16 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (`m95`).



## Captured run records

No records for this round are listed in the [run-record index](/downloads/results/run-records/index.json).


## Reproduction inventory

- **Type:** analysis-only
- **Script:** none published
- **Inputs:** `rounds/review-off-hard-1/MEASURED.md`, `rounds/review-off-hard-1/MISSING-DECLARED.json`, `rounds/review-off-hard-1/MISSING.md`, `rounds/review-off-hard-1/PLAN.json`, `rounds/review-off-hard-1/PRE-REVIEW-GRADES.json`, `rounds/review-off-hard-1/README.md`, `rounds/review-off-hard-1/bundles/rvo1/EXCLUDED.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r0/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r0/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r0/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r0/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r1/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r1/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r1/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-ex/r1/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r0/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r0/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r0/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r0/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r1/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r1/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r1/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/cron-go/r1/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r0/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r0/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r0/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r0/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r1/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r1/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r1/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-ex/r1/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r0/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r0/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r0/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r0/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r1/review-off/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r1/review-off/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r1/review-on/a1/attempt.json`, `rounds/review-off-hard-1/bundles/rvo1/attempts/vm-go/r1/review-on/a1/evaluation.json`, `rounds/review-off-hard-1/bundles/rvo1/frozen/experiment.toml`, `rounds/review-off-hard-1/bundles/rvo1/frozen/manifest.json`, `rounds/review-off-hard-1/bundles/rvo1/frozen/resolved/review-off.toml`, `rounds/review-off-hard-1/bundles/rvo1/frozen/resolved/review-on.toml`, `rounds/review-off-hard-1/bundles/rvo1/manifest.json`, `rounds/review-off-hard-1/bundles/rvo1/report.md`, `rounds/review-off-hard-1/records.jsonl`
- **Full execution replay:** unavailable
- **Scope:** Public bundles and records preserve observed Lab outcomes and configuration; model execution cannot be replayed from this repository snapshot.

See the [complete per-round reproduction inventory](/reproduce/) and the [repository reproduction guide](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/reproduce/README.md).

## Related records

### Related experiments

- [review-off-hard-1](/rounds/review-off-hard-1/)
