Round r64
r64
Source-reported narrativeRound README and results text are source material. Numeric values that are not tied to a claim ledger record remain source-reported.
Round source README · rounds/r64/README.md
Round date: HISTORICAL (before 2026-10-09) Publication badge: DESCRIPTIVE; KEPT FOR AUDIT Why not VALID: The historical inventory retains DESCRIPTIVE because of ENVIRONMENT, NO_PREREG_EVIDENCE, RECIPE. 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
DESCRIPTIVE
- NO_PREREG_EVIDENCE — Although the README reports a registration time, no retained timestamped registration artifact establishes that the rule predates the first result.
- RECIPE — The plan-shell implementation and task-selection recipe are not linked.
- 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.
STATUS: DESCRIPTIVE
Data completeness: 42.7% (51 deliveries; PASS WITH DECLARED GAPS). Measurement contract; declared gaps.
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: Round 64: Kogen plan-shell on selected Rails tasks in Studio, registered 4 October at approximately 18:45Z. The plan-shell implementation and task-selection recipe are not linked in the public record.
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-archive-book-access, rails-ar-bulk-access-grants, rails-as-variant-processed-once, rails-ft-active-storage-tracking, rails-ft-activity-feed-api, rails-ft-board-publish-unpublish-public-boundary, rails-ft-cancelled-account-cleanup, rails-ft-entropy-sweep, rails-ft-mysql-fulltext-search-foundation, rails-ft-notification-bundle-window-overlap, rails-hw-scoped-broadcast, rails-sec-audit-sweep, rails-sup-legacy-conversions
Task reconciliation: The surviving plan lists rails-ac-throttle-search, rails-aj-enqueue-after-commit, rails-ar-archive-book-access, rails-ar-bulk-access-grants, rails-as-variant-processed-once, rails-ft-active-storage-tracking, rails-ft-activity-feed-api, rails-ft-board-publish-unpublish-public-boundary, rails-ft-cancelled-account-cleanup, rails-ft-entropy-sweep, rails-ft-mysql-fulltext-search-foundation, rails-ft-notification-bundle-window-overlap, rails-hw-scoped-broadcast, rails-sec-audit-sweep, rails-sup-legacy-conversions. Task IDs in the public run-record export but not in that list: rails-ft-i18n-support, rails-ft-saas-billing. Listed task IDs with no matching tagged delivery: None. The public record does not establish intended reassignment or the reason for any mismatch; no run-record row was changed or reattributed. 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, 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, whose classifications can differ; see the register source crosswalk. 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 | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-aj-enqueue-after-commit | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-ar-archive-book-access | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-ar-bulk-access-grants | studio | kh-plan-shell | not re-derivable | 3 | 3 | 2 | 1 | 0 |
| rails-as-variant-processed-once | studio | kh-plan-shell | not re-derivable | 3 | 2 | 2 | 0 | 0 |
| rails-ft-active-storage-tracking | studio | kh-plan-shell | not re-derivable | 3 | 1 | 0 | 1 | 0 |
| rails-ft-activity-feed-api | studio | kh-plan-shell | not re-derivable | 3 | 3 | 2 | 1 | 0 |
| rails-ft-board-publish-unpublish-public-boundary | studio | kh-plan-shell | not re-derivable | 3 | 3 | 1 | 2 | 0 |
| rails-ft-cancelled-account-cleanup | studio | kh-plan-shell | not re-derivable | 3 | 2 | 2 | 0 | 0 |
| rails-ft-entropy-sweep | studio | kh-plan-shell | not re-derivable | 3 | 2 | 2 | 0 | 0 |
| rails-ft-i18n-support | studio | kh-plan-shell | not re-derivable | 3 | 0 | 0 | 0 | 0 |
| rails-ft-mysql-fulltext-search-foundation | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-ft-notification-bundle-window-overlap | studio | kh-plan-shell | not re-derivable | 3 | 1 | 0 | 1 | 0 |
| rails-ft-saas-billing | studio | kh-plan-shell | not re-derivable | 3 | 0 | 0 | 0 | 0 |
| rails-hw-scoped-broadcast | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-sec-audit-sweep | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 0 |
| rails-sup-legacy-conversions | studio | kh-plan-shell | not re-derivable | 3 | 3 | 3 | 0 | 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-cellsetup.kogen_shafield. - Harness source commit: not recorded. Per-cell
tools.harnessSHA-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-archive-book-access,rails-ar-bulk-access-grants,rails-as-variant-processed-once,rails-ft-active-storage-tracking,rails-ft-activity-feed-api,rails-ft-board-publish-unpublish-public-boundary,rails-ft-cancelled-account-cleanup,rails-ft-entropy-sweep,rails-ft-i18n-support,rails-ft-mysql-fulltext-search-foundation,rails-ft-notification-bundle-window-overlap,rails-ft-saas-billing,rails-hw-scoped-broadcast,rails-sec-audit-sweep,rails-sup-legacy-conversions. - 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.pyandpython3 reproduce/build_records.py; check this declaration withpython3 reproduce/validate_round.py --round r64. These commands regenerate or validate the archived public records. An original cell-launch command is not available. - Raw public records: r64.jsonl filtered by
audit_round/round_id, and cells.jsonl filtered byround.
Public snapshot rows for this tag: 51 captured deliveries (32 pass, 6 fail, 13 ungraded/unknown in results/run-records/r64.jsonl); official outcome export has 38 rows: 32 pass, 6 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: The historical 85-cell plan-shell headline is source-reported, not reproducible from public data. Keep r64, r64b, r64c, r64d and r64e as distinct captures; use the public Rails catalogue verification only for the explicitly recalculated export cohort.
Recomputed from raw records
`recomputed.json`, mined cell records, and the token audit back observed official outcomes, per-arm pass counts/rates, manifest token counters, and wall medians. The source contains 38 rows (fail 6, pass 32); overall pass rate is 84.2% (32/38) among pass/fail grades. Per-arm detail and coverage counts are in the JSON.
Published-export outcome cross-check: 38/38 shared cell IDs match; 0/38 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: 0/38 published metadata totals equal the manifest input + cached input + output sum; 38 differ (multi request aggregation 38). 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.
Published metadata vs raw manifest token counters (cell ID, published, manifest sum, provider response count, cause):
kh-gpt__gpt-6-luna__low__default__rails-ac-throttle-search__r1-kh-plan-shell-r64-studio: published1355669, manifest1346600, provider responses30;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ac-throttle-search__r2-kh-plan-shell-r64-studio: published754093, manifest745487, provider responses19;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ac-throttle-search__r3-kh-plan-shell-r64-studio: published830178, manifest822012, provider responses24;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-aj-enqueue-after-commit__r1-kh-plan-shell-r64-studio: published1837819, manifest1830266, provider responses33;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-aj-enqueue-after-commit__r2-kh-plan-shell-r64-studio: published1207414, manifest1199808, provider responses26;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-aj-enqueue-after-commit__r3-kh-plan-shell-r64-studio: published710313, manifest703112, provider responses22;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-archive-book-access__r1-kh-plan-shell-r64-studio: published798059, manifest790450, provider responses26;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-archive-book-access__r2-kh-plan-shell-r64-studio: published740728, manifest733123, provider responses16;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-archive-book-access__r3-kh-plan-shell-r64-studio: published741717, manifest734074, provider responses23;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-bulk-access-grants__r1-kh-plan-shell-r64-studio: published940828, manifest932418, provider responses25;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-bulk-access-grants__r2-kh-plan-shell-r64-studio: published3386226, manifest3379055, provider responses51;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ar-bulk-access-grants__r3-kh-plan-shell-r64-studio: published2613703, manifest2606394, provider responses39;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-as-variant-processed-once__r1-kh-plan-shell-r64-studio: published2152484, manifest2144803, provider responses38;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-as-variant-processed-once__r3-kh-plan-shell-r64-studio: published1351236, manifest1342701, provider responses30;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-active-storage-tracking__r1-kh-plan-shell-r64-studio: published7048679, manifest7028053, provider responses63;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-activity-feed-api__r1-kh-plan-shell-r64-studio: published2553755, manifest2533585, provider responses44;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-activity-feed-api__r2-kh-plan-shell-r64-studio: published3345515, manifest3325097, provider responses45;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-activity-feed-api__r3-kh-plan-shell-r64-studio: published1808871, manifest1788539, provider responses33;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-board-publish-unpublish-public-boundary__r1-kh-plan-shell-r64-studio: published3479429, manifest3459712, provider responses47;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-board-publish-unpublish-public-boundary__r2-kh-plan-shell-r64-studio: published3244283, manifest3224392, provider responses38;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-board-publish-unpublish-public-boundary__r3-kh-plan-shell-r64-studio: published3110818, manifest3091135, provider responses38;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-cancelled-account-cleanup__r2-kh-plan-shell-r64-studio: published5082110, manifest5062051, provider responses50;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-cancelled-account-cleanup__r3-kh-plan-shell-r64-studio: published5763836, manifest5743727, provider responses50;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-entropy-sweep__r1-kh-plan-shell-r64-studio: published1149898, manifest1129375, provider responses26;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-entropy-sweep__r2-kh-plan-shell-r64-studio: published2905706, manifest2885658, provider responses49;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r1-kh-plan-shell-r64-studio: published2424319, manifest2404069, provider responses37;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r2-kh-plan-shell-r64-studio: published2590709, manifest2570521, provider responses32;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r3-kh-plan-shell-r64-studio: published1438319, manifest1418102, provider responses30;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-ft-notification-bundle-window-overlap__r3-kh-plan-shell-r64-studio: published4312539, manifest4292097, provider responses52;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-hw-scoped-broadcast__r1-kh-plan-shell-r64-studio: published1489751, manifest1482333, provider responses32;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-hw-scoped-broadcast__r2-kh-plan-shell-r64-studio: published751717, manifest744173, provider responses22;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-hw-scoped-broadcast__r3-kh-plan-shell-r64-studio: published930027, manifest922516, provider responses28;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sec-audit-sweep__r1-kh-plan-shell-r64-studio: published1960326, manifest1952844, provider responses36;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sec-audit-sweep__r2-kh-plan-shell-r64-studio: published2735883, manifest2728527, provider responses45;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sec-audit-sweep__r3-kh-plan-shell-r64-studio: published3204959, manifest3197592, provider responses52;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sup-legacy-conversions__r1-kh-plan-shell-r64-studio: published813628, manifest805925, provider responses23;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sup-legacy-conversions__r2-kh-plan-shell-r64-studio: published2014090, manifest2006875, provider responses33;multi_request_aggregation.kh-gpt__gpt-6-luna__low__default__rails-sup-legacy-conversions__r3-kh-plan-shell-r64-studio: published1326810, manifest1319662, provider responses29;multi_request_aggregation.
Captured run records
Standard-schema records assigned to this round in the indexed snapshot.
Reproduction inventory
Published analysis replay and full experiment replay are reported separately.
- Replay type
unavailable- Script
- No per-round analysis script is published.
- Inputs
- No identified public input bundle.
- 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.
View the complete per-round reproduction inventory · Repository reproduction guide