Compute novelty score for a candidate descriptor via k-NN distance in archive descriptor space.
Compute novelty score for a candidate descriptor via k-NN distance in archive descriptor space.
npx skills add https://github.com/PAMF2/oniro-colab --skill novelty-bonus复制此命令并粘贴到 Claude Code 中以安装该技能
Stage 1 audit (ARIS §3.1). Verify the training run actually converged, seeds were logged, no data leakage.
Stage 3 audit (ARIS §3.1). Fresh zero-context reviewer re-reads wiki narrative; cross-checks against raw results.
Stage 2 audit (ARIS §3.1). For each experimental claim, decide supported / partially / invalidated against the logs.
On REJECT verdict, write a structured entry to the failure ledger so future executors skip the closed branch.
Read wiki frontier + failure ledger, emit one typed mutation as unified diff. Used by Executor agent.
After a mutation passes (or just falls in an empty novelty cell), update the MAP-Elites archive.
| name | novelty-bonus |
| description | Compute novelty score for a candidate descriptor via k-NN distance in archive descriptor space. |
| trigger | qd-archive-update |
| allowed_tools | ["python"] |
| output | json {novelty} |
Wraps oniro.orchestrator.novelty.novelty(archive, descriptor, k=5).
Called from qd-archive-update to decide whether a gate-rejected mutation still
warrants a provisional slot. Threshold: novelty > 0.7.
{ "novelty": 0.83 }