Round e06-context

e06 context

Status · PILOTReviewed 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/e06-context/README.md

Round date: HISTORICAL (before 2026-10-09) Publication badge: DESCRIPTIVE / INCOMPLETE (PILOT); KEPT FOR AUDIT Why not VALID: The historical inventory retains PILOT because of PRE_REGISTRATION_MISSING, RAW_EVIDENCE_MISSING, UNMATCHED_CONDITIONS. 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

PILOT

Why not VALID

  • PRE_REGISTRATION_MISSING: No pre-registered rule predating the pilot result is established.
  • UNMATCHED_CONDITIONS: Only one pilot cell is reported and no comparison arm was run.
  • RAW_EVIDENCE_MISSING: The B028 packet verifies one pass cell; the public exact-ID capture remains absent and the separate r1 ledger row has no manifest.

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.

Terminology: public round glossary.

STATUS: INTERIM

Data completeness: N/A (no exact-ID per-cell records in the public exports). Measurement record; declared gaps.

Pre-registered: not established in the public record; treat this as retrospective exploratory evidence. Hypothesis coverage: H54, H55 (provisional mapping; see the hypothesis register). Question: Does forced context compaction improve a Build relative to a matched uncompressed control? Population: One pilot cell is reported; no adjacent comparison arm is reported. Headline: No comparative efficacy claim.

Reported observations

  • The pilot is reported as 1/1 run with six effective compactions. (reported data; source-reported, not reproducible from public data.)
  • No adjacent comparison was run. (reported data; source-reported, not reproducible from public data.)

Reproduction and records

Required field Publicly recoverable value
Harness/Kogen revision Exact harness/Kogen revision is not recovered.
Model and effort Model and effort are not recovered.
Task IDs One pilot cell is reported; exact task ID is not recovered.
Command Not recovered; no public launch command or cell ID is available.
Raw records The exact-ID query returned zero rows in the committed public exports. Filtered Studio rows are linked in the source recovery section below; see reported-data.json for the public-export check.

The numerical observations above are documentary summaries, not a public exact-cell analysis. reported-data.json records each reported quantity and its status. The current public result files were checked for this exact round identifier; they do not provide this round's raw records.

Interpretation

Limitation: A single unpaired pilot cannot estimate a compaction treatment effect.

Smallest useful next test: Run matched forced-compaction and control cells under a frozen threshold, with exact context and outcome receipts.

No individual outcome should be promoted beyond the status above until the exact run records, grade identities, denominators and source revisions are reconciled.

Sources: reported data file; public cells export; public captured-delivery export.

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 2 rows (infra 1, pass 1); overall pass rate is 100.0% (1/1) among pass/fail grades. Per-arm detail and coverage counts are in the JSON.

No shared cell IDs are present in the committed public grade export; the source-only cohort is checked against the page's reported figures below. No shared public-export cell IDs are available for a paired outcome comparison. No complete published metadata/manifest token pairs are available for this round (0 missing manifest usage; 2 missing published metadata). Missing counters remain unknown, not zero. This round also has 2 raw-only or non-public rows; they are kept separate from the published-export denominator.

Captured run records

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

No per-round file is listed. Check the run-record index for the complete partition list.

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