Measured harness ledgerPublic result
GPT-6 Astra planner + Jev 1.13Dex Cube — 3 Move — GPT-6 Astra planner + Jev 1.13 Unreported
Complete the three-move Rubik's cube sequence D, F', U2 with regrasp, using two dexterous hands in MuJoCo.
Unreported reasoningHeadline result
- Workflow cost
- $5.92
- Wall-clock
- Not recorded
- Processed tokens
- Not recorded
- Record state
- operator_cut_unfinished_episode
Public summary
GPT-6 Astra planner + Jev 1.13 Unreported operator_cut_unfinished_episode ledger: Not recorded wall-clock, Not recorded, and $5.92 Recorded provider cost.
Run identity and stack
- Result ID: dex-cube-turn-mujoco-stage-2-three-moves-astra-jev-learn-cut-2026-09-21
- Technical model: GPT-6 Astra planner + Jev 1.13
- Provider: Provider not separately recorded
- Stack: Technical model/configuration: GPT-6 Astra planner + Jev 1.13
- Stack: MuJoCo dexterous-hand fixture
- Stack: Harness cube-turn stage-2 prompt
Validation evidence
- Path: artifacts/dex-cube-turn-mujoco-stage-2-three-moves-astra-jev-learn-cut-2026-09-21/validation/judge-replay.public.json
- SHA-256: fc38b6c7c2f9c25d40fee0703e207c962294e271d5a4a7198d5333b10f300b49
Recorded caveats
- NOT COMPARABLE WITH THE CODING-AGENT COHORTS OR WITH BARE DECISION-LOOP ROWS. This is a jev-astra-hybrid run: GPT-6 Astra and Jev 1.13 were coupled under a protocol that is not the one-shot locked-prompt coding-agent track and not the two-call-per-cycle decision-loop track. cohort_eligible is false. Harry's criterion (same verdict as Astra-alone AND cheaper on API-equivalent) is recorded in the track README; it is not a league-table standing.
- CUT. Do not resume. Not a completed learning-loop result.
Public result only
This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.