mirror of
https://github.com/ModernRelay/omnigraph.git
synced 2026-06-09 01:35:18 +02:00
cd291b9a1e
Add a "Next experiment candidates" section grouped by control-loop shape (the
unit of harness reuse is the loop, not the target):
Cluster A - reuses lance-autoresearch as-is:
A1. Adjacent distance kernels (cosine, dot, hamming)
A2. IVF partition-selection kernel (centroid scan)
A3. FTS BM25 scoring kernel
Cluster B - needs a new harness (BauplanLabs tournament loop):
B1. IVF_PQ index-build parameter tuning (original "surface 1")
B2. Auto-index-type selection (categorical + B1 inner)
Cluster C - highest ceiling, hardest harness:
C1. Physical-plan JSON patching for Lance-backed DataFusion
(literal BauplanLabs replication)
Each candidate notes the surface, oracle, harness reuse vs. new, and the
expected payoff. A cross-cluster section frames the three "if your goal is X,
run candidate Y next" branches: shortest path to upstream PR (A1), most
user-facing impact (B1), paper-publishable replication (C1). Includes the
go/no-go logic if A1 and B1 split.
scripts/check-agents-md.sh still passes (30/30 links).
https://claude.ai/code/session_01Aq8kBUcjmEPobcEufnWbW5
|
||
|---|---|---|
| .. | ||
| releases | ||
| research | ||
| architecture.md | ||
| audit.md | ||
| branch-protection.md | ||
| branches-commits.md | ||
| changes.md | ||
| ci.md | ||
| cli-reference.md | ||
| cli.md | ||
| codeowners.md | ||
| constants.md | ||
| deployment.md | ||
| embeddings.md | ||
| errors.md | ||
| execution.md | ||
| indexes.md | ||
| install.md | ||
| invariants.md | ||
| lance.md | ||
| maintenance.md | ||
| merge.md | ||
| policy.md | ||
| query-language.md | ||
| runs.md | ||
| schema-language.md | ||
| schema-lint.md | ||
| server.md | ||
| storage.md | ||
| testing.md | ||
| transactions.md | ||