AGENT SKILL

corpus-retrieval-lab

Benchmark current research-query and direct lexical baselines against experimental vector, BM25, typed concept-graph PPR, and RRF source selection without replacing production retrieval.

License 许可
MIT
所属仓库
jmagly/aiwg
最近更新
2026-11-12
Stars
★ 229
Forks
36

01 前言 Front Matter

name
corpus-retrieval-lab
triggers
[ "benchmark corpus retrieval", "hybrid retrieval lab", "compare research query retrieval" ]
namespace
aiwg
platforms
[ "all" ]
commandHint
{ "category": "research-retrieval", "allowedTools": "Read, Bash", "argumentHint": "--queries <jsonl> --concepts <json> [--expected-scheme-hash <sha256>] [--json] [--out <path>]" }
description
Benchmark current research-query and direct lexical baselines against experimental vector, BM25, typed concept-graph PPR, and RRF source selection without replacing production retrieval.

03 SKILL.md 正文

Corpus Retrieval Lab

Run the local experimental benchmark:

aiwg corpus retrieval-lab --queries <jsonl> --concepts <json> --json

Use reviewed narrow implementation questions with expected REF evidence. Preserve the current research-query behavior regardless of the result; the report may only recommend a later explicit adoption decision.

The lab reports baseline and hybrid Hit@k, MRR, latency, failures, confidence/dispersion, faithfulness, and concept-scheme drift. Use --expected-scheme-hash when comparing runs across time.

See docs/guides/corpus-retrieval-lab.md for fixture schemas and interpretation.

04 同仓库更多 Skills