> Data revision: baf7c2f4307d3a989a8fb9363df8000fda3d9310
> Source files:
- [rounds/r70-rve2/README.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/README.md)
- [rounds/r70-rve2/RESULTS.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/RESULTS.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)

# r70-rve2: Rust and Elixir round

**Round ID:** r70-rve2  
**Status:** INVALID

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

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

This INVALID Rust–Elixir comparison recorded Rust 4/9 versus Elixir 1/8 overall; these are descriptive results.

Round date: 2026-10-09
Publication badge: INVALID; KEPT FOR AUDIT
Why not VALID: TASK_MISMATCH, CONDITIONS_MISMATCH, RAW_EVIDENCE_PARTIAL — the registered comparison is invalid because tasks 5 and 7 used prompts that differed from their recorded originals.
Recomputation status: OBSERVED SOURCE ONLY

STATUS: **INVALID**

**Why this status:** The published task prompts for tasks 5 and 7 did not match their recorded original prompt hashes. This task-definition mismatch invalidates the registered comparison, so all outcomes are retained as descriptive evidence.

## How and where it ran

Runs used two Hetzner CCX13 Linux hosts, one in Europe and one in the US. The cells ran on 2026-10-09, approximately 08:11Z–09:14Z UTC. The configured model was gpt-6-luna at max effort. The Round 70 runner used agent client version 0.161.0 and a 3,600-second cell limit. Round 70 task kit as installed for this run; the surviving public record does not identify a complete kit revision.

The launcher argument was amended before any scored cell started. A descriptive peek after six complete pairs was Rust 1/6 and Elixir 0/6. The stop was issued after the task-prompt mismatch was confirmed; cells already running were allowed to finish. No replacements were recorded. The later task-1 cells passed, while the mismatched task-5 and task-7 results are not a valid language comparison.

Assigned cells ran serially on each host. The comparison was registered before any scored cell began.

## Lifecycle counts

| Phase | Count |
| --- | ---: |
| Planned | 36 |
| Started | 17 |
| Finished | 17 |
| Officially graded cells | 17 |
| ITT denominator | 36 |

A cell is one attempt at one task in one language; intention-to-treat (ITT) keeps assigned attempts in the analysis and counts timeouts as failures.

## Results

A full pass means the official task grade recorded a pass. Hidden suite test counts are shown as passed/total where they were captured; “0/—” means the tests did not run or no denominator is available. “Timeout” reports the runner time limit; “gate” reports the official full-pass result.

### Cell outcomes

| Cell | Task ID | Exact arm | Model / effort | Rep | Full outcome | Hidden suite tests passed / total | Timeout / gate flag |
| --- | --- | --- | --- | ---: | :---: | --- | --- |
| rve2-eu-p02-elixir | r70-7-elixir | elixir | gpt-6-luna / max | 1 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-eu-p02-rust | r70-7-rust | rust | gpt-6-luna / max | 1 | F | 23/24 | timeout: no; gate: fail; rc 129 |
| rve2-eu-p04-elixir | r70-5-elixir | elixir | gpt-6-luna / max | 1 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-eu-p04-rust | r70-5-rust | rust | gpt-6-luna / max | 1 | F | 22/24 | timeout: no; gate: fail; rc 1 |
| rve2-eu-p05-elixir | r70-1-elixir | elixir | gpt-6-luna / max | 2 | F | 24/25 | timeout: no; gate: fail; rc 1 |
| rve2-eu-p05-rust | r70-1-rust | rust | gpt-6-luna / max | 2 | P | 25/25 | timeout: no; gate: pass; rc 0 |
| rve2-eu-p06-elixir | r70-1-elixir | elixir | gpt-6-luna / max | 1 | P | 25/25 | timeout: no; gate: pass; rc 0 |
| rve2-eu-p06-rust | r70-1-rust | rust | gpt-6-luna / max | 1 | P | 25/25 | timeout: no; gate: pass; rc 0 |
| rve2-us-p01-elixir | r70-5-elixir | elixir | gpt-6-luna / max | 2 | F | 22/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p01-rust | r70-5-rust | rust | gpt-6-luna / max | 2 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p03-elixir | r70-5-elixir | elixir | gpt-6-luna / max | 3 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p03-rust | r70-5-rust | rust | gpt-6-luna / max | 3 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p07-elixir | r70-7-elixir | elixir | gpt-6-luna / max | 3 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p07-rust | r70-7-rust | rust | gpt-6-luna / max | 3 | F | 23/24 | timeout: no; gate: fail; rc 1 |
| rve2-us-p08-elixir | r70-1-elixir | elixir | gpt-6-luna / max | 3 | F | 24/25 | timeout: no; gate: fail; rc 1 |
| rve2-us-p08-rust | r70-1-rust | rust | gpt-6-luna / max | 3 | P | 25/25 | timeout: no; gate: pass; rc 0 |
| rve2-us-p10-rust | r70-1-rust | rust | gpt-6-luna / max | 3 | P | 25/25 | timeout: no; gate: pass; rc 0 |

## Per-language summary

Across all completed cells, Rust had 4 full passes in 9 cells and Elixir had 1 in 8. The six-pair descriptive peek before the stop was Rust 1/6 and Elixir 0/6. All results remain descriptive because the task prompts for tasks 5 and 7 mismatched their recorded originals.

## Reproduction metadata

- Kogen commit: not recorded in the surviving public source.
- Harness commit: not recorded in the surviving public source.
- Model and effort: gpt-6-luna at max.
- Task IDs: r70-1-elixir, r70-1-rust, r70-5-elixir, r70-5-rust, r70-7-elixir, r70-7-rust.
- Historical command: exact invocation is not retained; the recorded setup used the Round 70 runner described above.
- Raw records: [per-cell Standard records](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/records.jsonl); [cell outcomes](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/RESULTS.md); [filtered grade and audit extracts](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/pulled-all/).

## What's missing and why
- `circumstances.concurrent_cells_end` (17 missing): Host-wide concurrent cell count was not captured Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.concurrent_cells_start` (17 missing): Host-wide concurrent cell count was not captured Reason: Host-wide concurrent cell count was not captured (`m66`).
- `circumstances.dispatcher_id` (17 missing): Per-cell dispatcher revision is not present in the public round data Reason: Per-cell dispatcher revision is not present in the public round data (`m72`).
- `circumstances.incidents` (17 missing): Per-cell incident receipt was not captured Reason: Per-cell incident receipt was not captured (`m78`).
- `circumstances.load1_end` (17 missing): 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` (17 missing): 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` (17 missing): Timestamped host-wide load samples were not captured Reason: Timestamped host-wide load samples were not captured (`m93`).
- `circumstances.queue` (17 missing): Queue receipt was not captured Reason: Queue receipt was not captured (`m91`).
- `cost.calculator_version` (17 missing): Cost calculator version not recorded Reason: Cost calculator version not recorded (`m61`).
- `cost.price_table_version` (17 missing): Price table version not recorded Reason: Price table version not recorded (`m89`).
- `cost.usd` (17 missing): 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`).
- `environment.account_class` (17 missing): Dated account-class receipt is not present in the public round data Reason: Dated account-class receipt is not present in the public round data (`m62`).
- `environment.network.allowlist_hosts` (17 missing): 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.toolchains.elixir` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.erlang` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.node` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `environment.toolchains.other_inventory` (17 missing): Full per-cell toolchain inventory not recorded Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `environment.toolchains.ruby` (17 missing): Toolchain inventory not recorded Reason: Toolchain inventory not recorded (`m94`).
- `environment.toolchains.rust` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `grade.grader` (17 missing): 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` (17 missing): Per-cell official repair-grade timestamp is not present in the public data/cells.csv or sanitized lane release-state receipt Reason: Per-cell official repair-grade timestamp is not present in the public data/cells.csv or sanitized lane release-state receipt (`m81`).
- `sandbox.egress_allow` (17 missing): 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.profile` (17 missing): 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` (17 missing): 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.deps_source` (17 missing): Per-cell dependency source is not recorded Reason: Per-cell dependency source is not recorded (`m71`).
- `setup.sandbox_mode` (17 missing): 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` (17 missing): 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`).
- `timestamps.attempts` (17 missing): Attempt-boundary receipts are not in the public round data Reason: Attempt-boundary receipts are not in the public round data (`m60`).
- `timestamps.phases.develop.end_utc` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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` (17 missing): 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.develop` (17 missing): develop phase timing was not separately recorded in the public round data Reason: develop phase timing was not separately recorded in the public round data (`m96`).
- `timing.phases_s.grade` (17 missing): grade phase timing was not separately recorded in the public round data Reason: grade phase timing was not separately recorded in the public round data (`m98`).
- `timing.phases_s.setup` (17 missing): setup phase timing was not separately recorded in the public round data Reason: setup phase timing was not separately recorded in the public round data (`m99`).
- `tokens.phases.develop.cached_input` (17 missing): develop phase token counter was not recorded separately Reason: develop phase token counter was not recorded separately (`m97`).
- `tokens.phases.develop.input` (17 missing): develop phase token counter was not recorded separately Reason: develop phase token counter was not recorded separately (`m97`).
- `tokens.phases.develop.output` (17 missing): develop phase token counter was not recorded separately Reason: develop phase token counter was not recorded separately (`m97`).
- `tokens.phases.develop.reasoning` (17 missing): develop phase token counter was not recorded separately Reason: develop phase token counter was not recorded separately (`m97`).
- `tools.grader` (17 missing): 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` (17 missing): 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.toolchains.elixir` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.erlang` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.node` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).
- `tools.toolchains.other_inventory` (17 missing): Full per-cell toolchain inventory not recorded Reason: Full per-cell toolchain inventory not recorded (`m64`).
- `tools.toolchains.ruby` (17 missing): Toolchain inventory not recorded Reason: Toolchain inventory not recorded (`m94`).
- `tools.toolchains.rust` (17 missing): Toolchain version not recorded Reason: Toolchain version not recorded (`m95`).

## Records and methods

The per-cell Standard records are in [records.jsonl](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/records.jsonl). The complete result table and launcher details are in [RESULTS.md](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/RESULTS.md); filtered grade fields, audit counts, and launcher extracts are in [pulled-all](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/pulled-all/). See [the measurement contract](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/MEASURED.md), [the registered plan](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/PLAN.json), and [the decision rule](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/DECISION-RULE.md).


## Results source

# rve2 results

**STATUS: INVALID.** The prompt mismatch on tasks 5 and 7 compromises the registered comparison. Every available outcome below is descriptive and must not be used as a valid Rust–Elixir comparison.

The launcher stopped after the mismatch was identified. The descriptive peek recorded six complete pairs at that point: Rust 1/6, Elixir 0/6. Later cells that finished before the stop remain individually listed below; the peek is not a tally of the full set. `rc` and wall time come from the filtered launcher START/END lines. Test totals and outcomes are official per-cell fields.

| Cell | Task | Exact arm label | pass_ outcome | Tests | Failures + errors | Tests ran | Launcher rc | Wall s |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| rve2-eu-p02-elixir | r70-7-elixir | elixir | pass_=false | 24 | 1 | yes | 1 | 330 |
| rve2-eu-p02-rust | r70-7-rust | rust | pass_=false | 24 | 1 | yes | 129 | 160 |
| rve2-eu-p04-elixir | r70-5-elixir | elixir | pass_=false | 24 | 1 | yes | 1 | 501 |
| rve2-eu-p04-rust | r70-5-rust | rust | pass_=false | 24 | 2 | yes | 1 | 290 |
| rve2-eu-p05-elixir | r70-1-elixir | elixir | pass_=false | 25 | 1 | yes | 1 | 941 |
| rve2-eu-p05-rust | r70-1-rust | rust | pass_=true | 25 | 0 | yes | 0 | 360 |
| rve2-eu-p06-elixir | r70-1-elixir | elixir | pass_=true | 25 | 0 | yes | 0 | 720 |
| rve2-eu-p06-rust | r70-1-rust | rust | pass_=true | 25 | 0 | yes | 0 | 270 |
| rve2-us-p01-elixir | r70-5-elixir | elixir | pass_=false | 24 | 2 | yes | 1 | 521 |
| rve2-us-p01-rust | r70-5-rust | rust | pass_=false | 24 | 1 | yes | 1 | 220 |
| rve2-us-p03-elixir | r70-5-elixir | elixir | pass_=false | 24 | 1 | yes | 1 | 480 |
| rve2-us-p03-rust | r70-5-rust | rust | pass_=false | 24 | 1 | yes | 1 | 210 |
| rve2-us-p07-elixir | r70-7-elixir | elixir | pass_=false | 24 | 1 | yes | 1 | 430 |
| rve2-us-p07-rust | r70-7-rust | rust | pass_=false | 24 | 1 | yes | 1 | 160 |
| rve2-us-p08-elixir | r70-1-elixir | elixir | pass_=false | 25 | 1 | yes | 1 | 1061 |
| rve2-us-p08-rust | r70-1-rust | rust | pass_=true | 25 | 0 | yes | 0 | 370 |
| rve2-us-p10-rust | r70-1-rust | rust | pass_=true | 25 | 0 | yes | 0 | 260 |

## Corrected audit

The corrected per-cell count export is [`audit-corrected.jsonl`](https://github.com/KogenAI/kogen-bench/blob/baf7c2f4307d3a989a8fb9363df8000fda3d9310/rounds/r70-rve2/pulled-all/audit-corrected.jsonl). It covers all 17 available cells across both hosts; 0 cells were flagged. The registered round is still INVALID because of the task prompt mismatch.


## 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:** Only filtered grade and manifest fields, selected launcher lines, and corrected audit counts are available; no complete delivery bundle or execution replay is published.

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

- [r70-rve2](/rounds/r70-rve2/)
