Measured harness ledgerPublic result
Laya 421MApple Carry — Laya 421M Unreported
Carry an apple onto a plate on two embodiments: an xArm7 in OpenRoboto's MuJoCo scene, and an FR3 with a Robotiq 2F-85 on SuperDex.
Unreported reasoningHeadline result
- Workflow cost
- $0.00
- Wall-clock
- Not recorded
- Processed tokens
- Not recorded
- Record state
- judge_verified_decision_loop_sweep_independently_replayed
Public summary
Laya 421M Unreported judge_verified_decision_loop_sweep_independently_replayed ledger: Not recorded wall-clock, Not recorded, and $0.00 Recorded provider cost.
Run identity and stack
- Result ID: apple-carry-xarm7-openroboto-laya-421m-decision-loop-local-2026-09-20
- Technical model: Laya 421M
- Provider: local (MPS)
- Client: unix-socket Laya server, batch size 1, nice -n 10
- Stack: local (MPS)
- Stack: unix-socket Laya server, batch size 1, nice -n 10
- Stack: Technical model/configuration: Laya 421M
- Stack: Embodied manipulation fixture
- Stack: Harness apple-carry prompt
Validation evidence
- Path: artifacts/apple-carry-xarm7-openroboto-laya-421m-decision-loop-local-2026-09-20/validation/judge-replay.public.json
- SHA-256: e42c1c7d63ef727bd5951c5afc580af6a0a9d86225a3c89fd1a5b901ff2cb27f
- Validator SHA-256: 5facf7bb27541fca9a60dbaaded91151a3e4f9962419bfd55877bd0b49db5d81
Recorded caveats
- NOT COMPARABLE WITH THE CODING-AGENT COHORTS. Every coding-agent result in this harness came from an agent with a shell, the fixture workspace, hours of wall clock and unlimited self-play against the simulator, submitting a controller it had already debugged. This is a decision-loop run: the model saw one structured observation at a time, answered two typed multiple-choice questions per control cycle (one intent, then the per-channel directions), and never wrote code, never ran the simulator, never saw an image and never read the judge. The executor that performed the increments is HARNESS-AUTHORED, not model-authored. Cycles, cost, wall clock and outcome mean different things in the two tracks and must never be put in one league table. cohort_eligible is false for exactly this reason.
- 0/20. intent=carry and gripper=open on all 3200 cycles. qpos replay error 0.0.
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.