Round r56d

r56d

Status · INCOMPLETEReviewed status is transcribed from rounds/STATUS.md. The original narrative and its qualifications remain below.

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/r56d/README.md

Round date: HISTORICAL (before 2026-10-09) Publication badge: INCOMPLETE; KEPT FOR AUDIT Why not VALID: The historical inventory retains INCOMPLETE because of CROSSWALK, DESIGN, 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 — No public predeclared decision rule was recovered.
  • CROSSWALK — Official outcomes cannot be matched to the prior builder-context and P-noctx2 rows.
  • DESIGN — The dedicated design section and exact arm specification 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.
  • 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: INCOMPLETE

Data completeness: 38.9% (37 deliveries; PASS WITH DECLARED GAPS). Measurement contract; declared gaps.

Status reason: Official cells outcomes cannot be matched to the prior builder-context and P-noctx2 arm rows; the table and result summary are removed.

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; no outcome comparison is reported.

Arms: Exact arm recipes are not recoverable from the public record; the previous label table is removed pending a cell-level crosswalk.

Planned tasks in the surviving round note: 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: Outcome interpretation is withheld because the official cells export and captured run-record export cannot be crosswalked for this round. No benchmark comparison is reported.

Public outcome reconciliation status

The prior delivery and outcome table is removed because its arm labels or outcome totals do not match the official cells export. The captured-delivery ledger remains available in r56d.jsonl; no combined result is reported here.

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, b5a8d85d4bdcb8fa2445e42690dabc90bdde5b912e7b26c7ef5ba69b4dee8abb. 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; kh-gpt: model requested/effective gpt-6-luna → not recorded (Not recorded in available public metadata); effort requested/effective low → not recorded (Not recorded in available public metadata); kh-plan: model requested/effective gpt-6-luna → chatgpt/gpt-6-luna; effort requested/effective max → xhigh; runner requested low.
  • Observed task IDs: 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 r56d. These commands regenerate or validate the archived public records. An original cell-launch command is not available.
  • Raw public records: r56d.jsonl filtered by audit_round/round_id, and cells.jsonl filtered by round.

Public snapshot rows for this tag: 37 captured deliveries (12 pass, 2 fail, 23 ungraded/unknown in results/run-records/r56d.jsonl); official outcome export has 14 rows: 12 pass, 2 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: This validity/correction capture remains separate from r56, r56b, r56c and r56p2. The public ledger does not establish a complete original arm comparison.

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 14 rows (fail 2, pass 12); overall pass rate is 85.7% (12/14) among pass/fail grades. Per-arm detail and coverage counts are in the JSON.

Published-export outcome cross-check: 14/14 shared cell IDs match; 0/14 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: 3/14 published metadata totals equal the manifest input + cached input + output sum; 11 differ (multi request aggregation 11). 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-aj-enqueue-after-commit__r1-P-full-r56d-studio: published 2812589, manifest 2013886, provider responses 44; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ar-bulk-access-grants__r1-P-noctx2-r56d-studio: published 3217337, manifest 2590734, provider responses 59; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-as-variant-processed-once__r1-P-noctx2-r56d-studio: published 3441900, manifest 3062213, provider responses 46; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-as-variant-processed-once__r2-P-noctx2-r56d-studio: published 3964455, manifest 3542441, provider responses 59; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-as-variant-processed-once__r3-P-noctx2-r56d-studio: published 3591397, manifest 2992726, provider responses 48; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r2-P-full-r56d-studio: published 3226472, manifest 2258224, provider responses 50; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r2-P-noreview-r56d-studio: published 3350450, manifest 2221925, provider responses 41; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r3-P-nocontract-r56d-studio: published 2702389, manifest 1820995, provider responses 38; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r3-P-noreview-r56d-studio: published 2906991, manifest 2015616, provider responses 39; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r4-P-nocontract-r56d-studio: published 4729823, manifest 3648841, provider responses 60; multi_request_aggregation.
  • kh-gpt__gpt-6-luna__low__default__rails-ft-mysql-fulltext-search-foundation__r4-P-noreview-r56d-studio: published 4977917, manifest 3927002, provider responses 61; multi_request_aggregation.

Captured run records

Standard-schema records assigned to this round in the indexed snapshot.

37 records · 266,931 bytesDownload r56d.jsonl · View immutable source ↗

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