Martin Vogel 16034f21a8 docs(eval-plan): ground D1-D5 in the literature and external QA benchmarks ...

Address peer-review feedback on question provenance/external validity.

- Anchor the five dimensions to Sillito, Murphy & De Volder's catalogue of
  questions programmers ask during software-evolution tasks (FSE'06/TSE'08),
  with LaToza & Myers (2010) and Ko et al. (ICSE'07) as support; add a
  D1-D5 -> Sillito-group mapping table
- Adopt published repo-level QA benchmarks for the major languages: reuse and
  compare against SWE-QA (primary), with CoReQA, CodeRepoQA and RepoQA as
  references; note snippet-level sets (CodeQA/CS1QA/CoSQA) as the contrast
  that motivates structural retrieval
- Policy: anchor to Sillito; reuse SWE-QA for major languages; generate the
  multilingual remainder from independent LSP/git ground truth, never from
  the model under test

2026-06-06 11:49:48 +02:00

..

BENCHMARK.md

docs(benchmark): final PHP-LSP numbers — 278 tests, ~10k LoC

2026-05-09 16:06:20 +02:00

EVALUATION_PLAN.md

docs(eval-plan): ground D1-D5 in the literature and external QA benchmarks

2026-06-06 11:49:48 +02:00

graph-ui-screenshot.png

Update README + website: performance-first messaging, graph UI, 8 agents

2026-03-19 23:35:30 +01:00

index.html

Advertise semantic search and correct language count across docs

2026-06-05 18:48:41 +02:00

llms.txt

Advertise semantic search and correct language count across docs

2026-06-05 18:48:41 +02:00

robots.txt

docs: rebuild landing page, update facts and add GEO/SEO + live releases

2026-06-01 21:12:06 +02:00

sitemap.xml

Advertise semantic search and correct language count across docs

2026-06-05 18:48:41 +02:00