> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [rounds/r57d/README.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r57d/README.md)
- [results/run-records/index.json](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/index.json)
- [results/run-records/r57d.jsonl](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/r57d.jsonl)
- [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)

# r57d

**Round ID:** r57d  
**Status:** INCOMPLETE

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

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

Round date: HISTORICAL (before 2026-10-09)
Publication badge: INCOMPLETE; KEPT FOR AUDIT
Why not VALID: The historical inventory retains INCOMPLETE because of DESIGN, ENVIRONMENT, NO_PREREG. See the round evidence and limitations below.
Recomputation status: OBSERVED SOURCE ONLY



**Recomputation update:** The mined raw records now provide per-cell outcome, manifest token-counter, and wall-time recomputation for the observed cohort. This does not reconstruct missing planned cells, a full intention-to-treat denominator, or model execution.
## Status

**INCOMPLETE**

- NO_PREREG — The README records no pre-registration.
- DESIGN — The dedicated design section and a testable question are absent.
- ENVIRONMENT — Planned task-to-environment assignments are not established.

## Required reproduction metadata

- Kogen commit: not recorded in the cited round source.
- Harness commit: not recorded in the cited round source as a Git commit; any adapter or runtime fingerprints are not Git commits.
- Model and effort: a complete per-cell mapping is not recorded in the cited round source; values present in the source summary remain as stated above.
- Raw records: the cited sources do not provide a complete public round-specific request and grade bundle; public delivery and outcome exports are linked above where applicable.


Terminology: [public round glossary](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/GLOSSARY.md).

STATUS: **INCOMPLETE**

Data completeness: **48.5%** (97 deliveries; PASS WITH DECLARED GAPS). [Measurement contract](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r57d/MEASURED.md); [declared gaps](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r57d/MISSING.md).














Status reason: Documentary capture only; the surviving public record does not establish a testable research question or a complete comparison protocol, so no research conclusion is claimed.



Pre-registered: no


Lifecycle: Historical capture; closure is not independently reconciled from the public record.

Question: No testable research question is recoverable from the committed public record; this page is a documentary delivery inventory, not an interpretable study.
Design: The dedicated design section was not located.

Venue: Public host identifiers are listed in the reconciliation table. The surviving record does not establish every planned task-to-host assignment or the execution-environment details.

Decision rule: No public predeclared decision rule was recovered; outcome counts below are descriptive.

Arms: Arm definitions are not re-derivable from the public record; exported labels appear in the reconciliation table below.

Planned tasks in the surviving round note: rails-ac-throttle-search, rails-aj-enqueue-after-commit, rails-ar-bulk-access-grants, rails-as-variant-processed-once, rails-ft-mysql-fulltext-search-foundation, rails-hw-scoped-broadcast

Verdict: Public run-record outcomes are summarized below. No comparison claim is made where the arm definition, decision rule or source report is not re-derivable.

## Public delivery and outcome reconciliation

This captured-delivery summary uses the public [run-record export](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/r57d.jsonl), grouped by audit round, task ID, public host ID, and the exact exported arm label. Captured counts rows; graded counts rows marked `graded=true`; pass, fail, and other are the run-record outcome fields. Official outcome states are in [cells.jsonl](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/cells.jsonl), whose classifications can differ; see the [register source crosswalk](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/README.md). Planned n is shown only when source-reported; unknown allocations are not inferred.

| Task ID | Public host ID | Arm label in export | Planned n | Captured | Graded | Pass | Fail | Other graded outcome |
|---|---|---|---:|---:|---:|---:|---:|---:|
| rails-ac-throttle-search | studio | default-tools | not re-derivable | 8 | 8 | 6 | 2 | 0 |
| rails-ac-throttle-search | studio | shell-only | not re-derivable | 8 | 8 | 6 | 2 | 0 |
| rails-aj-enqueue-after-commit | studio | default-tools | not re-derivable | 8 | 8 | 8 | 0 | 0 |
| rails-aj-enqueue-after-commit | studio | shell-only | not re-derivable | 8 | 8 | 8 | 0 | 0 |
| rails-ar-bulk-access-grants | studio | default-tools | not re-derivable | 8 | 8 | 7 | 1 | 0 |
| rails-ar-bulk-access-grants | studio | shell-only | not re-derivable | 8 | 8 | 8 | 0 | 0 |
| rails-as-variant-processed-once | studio | default-tools | not re-derivable | 8 | 8 | 1 | 7 | 0 |
| rails-as-variant-processed-once | studio | shell-only | not re-derivable | 8 | 8 | 4 | 4 | 0 |
| rails-ft-mysql-fulltext-search-foundation | studio | default-tools | not re-derivable | 8 | 8 | 0 | 8 | 0 |
| rails-ft-mysql-fulltext-search-foundation | studio | shell-only | not re-derivable | 9 | 8 | 0 | 8 | 0 |
| rails-hw-scoped-broadcast | studio | default-tools | not re-derivable | 8 | 8 | 8 | 0 | 0 |
| rails-hw-scoped-broadcast | studio | shell-only | not re-derivable | 8 | 8 | 7 | 1 | 0 |

## Reproduction record and source reconciliation

This section documents exact replay limits and keeps the page lifecycle and earlier statuses unchanged.

- Kogen source commit: `not applicable (Harness does not use Kogen)` in the per-cell `setup.kogen_sha` field.
- Harness source commit: not recorded. Per-cell `tools.harness` SHA-256 fingerprint(s): `562c489daaf10a03c06d3a86f8227bf08b6a43096f6fae9fd0b5f59bda4e7371`. Only wrapper fingerprints are public; the underlying source commit remains unrecorded.
- Models and effort (requested → effective): `kh-gpt: model requested/effective gpt-6-luna → chatgpt/gpt-6-luna; effort requested/effective low → xhigh`; `kh-gpt: model requested/effective gpt-6-luna → chatgpt/gpt-6-luna; effort requested/effective max → xhigh; runner requested low`.
- Observed task IDs: `rails-ac-throttle-search`, `rails-aj-enqueue-after-commit`, `rails-ar-bulk-access-grants`, `rails-as-variant-processed-once`, `rails-ft-mysql-fulltext-search-foundation`, `rails-hw-scoped-broadcast`.
- Original execution command: not recorded in the public snapshot; the benchmark cells cannot be replayed from this repository.
- Rebuild the public metadata from the repository root with `python3 reproduce/export_results.py` and `python3 reproduce/build_records.py`; check this declaration with `python3 reproduce/validate_round.py --round r57d`. These commands regenerate or validate the archived public records. An original cell-launch command is not available.
- Raw public records: [r57d.jsonl](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/r57d.jsonl) filtered by `audit_round`/`round_id`, and [cells.jsonl](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/cells.jsonl) filtered by `round`.

Public snapshot rows for this tag: 97 captured deliveries (63 pass, 33 fail, 1 ungraded/unknown in `results/run-records/r57d.jsonl`); official outcome export has 96 rows: 63 pass, 33 fail in `cells.jsonl`. These are separate source totals. The public files do not provide a complete joined intention-to-treat result.

**Round-specific reconciliation:** Keep this Rails lane separate from r57/r57b/r57c and r57e. Public delivery rows do not establish the historical pooled non-inferiority analysis.

## Recomputed from raw records

[`recomputed.json`](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r57d/recomputed.json), [mined cell records](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/data/mined/r57d.jsonl.gz), and the [token audit](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/data/mined/TOKEN-AUDIT.json) back observed official outcomes, per-arm pass counts/rates, manifest token counters, and wall medians. The source contains 96 rows (fail 33, pass 63); overall pass rate is 65.6% (63/96) among pass/fail grades. Per-arm detail and coverage counts are in the JSON.

Published-export outcome cross-check: 96/96 shared cell IDs match; 0/96 public-export rows have no mined source record. Exact IDs and results for unpaired rows are in `recomputed.json`.
No per-cell outcome mismatches were found in the shared IDs.
Token reconciliation under [METHOD.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/METHOD.md): 96/96 published metadata totals equal the manifest `input + cached input + output` sum; 0 differ (no mismatches). Reasoning remains a separate reported component and is not added to output.
The recompute keeps both numbers visible. 0 unexplained single-response numeric errors were identified; multi-response rows retain the published full-cell total and the manifest counter separately because per-response usage records are excluded.


## Captured run records

[results/run-records/r57d.jsonl](/downloads/results/run-records/r57d.jsonl) · 97 records · 645,063 bytes · [immutable source](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/results/run-records/r57d.jsonl).


## Reproduction inventory

- **Type:** unavailable
- **Script:** none published
- **Inputs:** none identified
- **Full execution replay:** unavailable
- **Scope:** No public per-round analysis script with a complete, identified input bundle is published. See the round README, MEASURED.md, and MISSING.md for recorded scope and gaps; historical execution inputs/toolchains/grading are not bundled.

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

- [r57d](/rounds/r57d/)

### Related claims

- [CL-WA-r57d-public-export-coverage](/claims/cl-wa-r57d-public-export-coverage/)
