> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [rounds/jev-route-ctx/README.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/jev-route-ctx/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)

# Jev route with prepared context

**Round ID:** jev-route-ctx  
**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.

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


**Recomputation limit:** Published summary figures: planned/observed counts, outcome totals/rates, and numeric estimates as present in README.md and RESULTS.md. These figures cannot be recomputed from repository inputs because 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.
## Status

**DESCRIPTIVE**

### Why not VALID
- **POST_HOC_DIAGNOSTIC:** This is an offline routing diagnostic, not a pre-registered live efficacy comparison.
- **RAW_EVIDENCE_MISSING:** The route log and reference labels are absent.


## 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.


STATUS: **INTERIM** — Offline routing diagnostic; route agreement is not Build success. Study figures in the result section are source-reported, not reproducible from public data. The accounting table classifies this as an offline analysis; its zero live Build counts are not measured outcomes. The route log is not included in this public page.

## Scope and reported result

The study compared a context-prepared Jev route with reference routes on 18 tasks. The source identifies Jev 1.13 / route-v3 and reports 10 of 18 reference matches, misses on all 3 large tasks, and 54 of 54 repeated decisions agreeing. A separate Sol route-v3 modal reference match rate is reported as 11 of 18. The supplied summary says exact context-version scores are in the source receipt, but does not provide them here.

Repeat agreement measures consistency, not accuracy. These results do not show that a route improves live Build success, cost or time, and they do not establish a dispatch policy.

## Live Build accounting

| planned_n | started_n | finished_n | graded_n | itt_n |
|---:|---:|---:|---:|---:|
| 0 | 0 | 0 | 0 | 0 |

This page covers an offline route diagnostic, not a live Build cohort. Route comparisons are separate analysis units.

## Reproduction record

| Field | Record |
|---|---|
| Harness / Kogen commit | No live harness or Kogen execution is described. |
| Model and effort | Jev 1.13 / route-v3 is source-reported. The Sol route-v3 comparison's exact model and effort are not supplied. |
| Task IDs | The exact task IDs are not supplied in a sanitized public list. |
| Command | The exact route-generation command is not recovered from the supplied public input. |
| Raw records | The source inventory names `jev-route-ctx-log.jsonl`; the route log and reference labels are not included in the public data tree. |

Until the exact task list and context-version records are published, all figures remain source-reported, not reproducible from public data.


## Captured run records

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


## 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

- [jev-route-ctx](/rounds/jev-route-ctx/)

### Related claims

- [CL-WA-jev-route-ctx-reported-observation](/claims/cl-wa-jev-route-ctx-reported-observation/)
