mirror of
https://github.com/lightningnetwork/lnd.git
synced 2026-08-20 13:27:27 +02:00
5200d1fc07
In this commit, we land the verdict for the two Opus 5 reflection arms and close exp-010. The headline: opus-default produced the first evolved candidate to statistically tie a champion on any tier (split-val +0.005 vs mx_c3, higher raw success), evolving persistent parallel flow plans, concurrency-first dispatch, and residual-aware shard budgeting across 1,931 lines -- then paid for that corridor depth with a collapse on every off-corpus tier (hard test 0.303 vs 0.583). The medium-effort arm is the cautionary tale: best val score of the family, worst held-out -- caught by the sealed sweep exactly as intended. Champions remain hb1 + mx_c3, now validated against three proposer lineages on this corpus. At fixed eval budget, reflection quality beats reflection throughput; proposer strength moves candidates along the specialist-generalist axis rather than lifting the curve. Both winners are archived, exploit-grep clean. |
||
|---|---|---|
| .. | ||
| exp-001-param-smoke.md | ||
| exp-002-param-run1.md | ||
| exp-003-seed-router-vs-lnd.md | ||
| exp-004-code-evolution.md | ||
| exp-004-sim-audit.md | ||
| exp-005-sim-audit.md | ||
| exp-006-breakthrough.md | ||
| exp-007-mix-followup.md | ||
| exp-008-drift-evolution.md | ||
| exp-008-drift1-best-candidate.go | ||
| exp-008-drift1-best-candidate.md | ||
| exp-009-mainnet-validation.md | ||
| exp-010-opus1-best-candidate.go | ||
| exp-010-opusmed1-best-candidate.go | ||
| exp-010-split2-best-candidate.go | ||
| exp-010-splitting-pressure.md | ||
| exp-011-code-gen2.md | ||
| exp-011-gen2-best-candidate.go | ||