This commit is contained in:
Aaron Po
2026-08-31 18:33:20 -04:00
parent 30995f6f40
commit 772a65d896
11 changed files with 353 additions and 218 deletions

View File

@@ -1,4 +1,13 @@
# Ethics, bias, and known issues
---
title: Pipeline ethics, bias, and known issues
last-updated: 2026-08-31
tags:
- pipeline
- ethics
- bias
- known-issues
- ai-generated
---
This document covers the ethical context of the Biergarten Pipeline's output,
the model's biases, and known issues including hallucinated brewing science and
@@ -290,11 +299,11 @@ Each brewery and user address carries a longitude/latitude pair, sampled
uniformly at random within a 5 km disc centred on the city's curated
`latitude`/`longitude` from `locations.json`.
The resulting point is **plausible by construction**, always falling within
the city's vicinity, but it is not looked up from any real address registry.
It does not correspond to a real address, business, or resident, and should
not be treated as accurate geocoding data. This is consistent with the rest of
the dataset: fixture data for a proof-of-concept, not a source of truth.
The resulting point is **plausible by construction**, always falling within the
city's vicinity, but it is not looked up from any real address registry. It does
not correspond to a real address, business, or resident, and should not be
treated as accurate geocoding data. This is consistent with the rest of the
dataset: fixture data for a proof-of-concept, not a source of truth.
---

View File

@@ -1,4 +1,13 @@
# Biergarten Pipeline
---
title: Biergarten Pipeline — C++ CLI for generating seed data
last-updated: 2026-08-31
tags:
- pipeline
- cpp
- llm
- seed-data
- docker
---
A C++20 command-line pipeline that samples city records from local JSON,
enriches each with Wikipedia context, and generates bilingual brewery names and
@@ -436,8 +445,8 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
Paths below are relative to `tooling/pipeline/`.
- `src/main.cc`: argument parsing and DI composition root.
- `src/biergarten_pipeline_orchestrator/`: orchestration, sampling, logging,
and export.
- `src/biergarten_pipeline_orchestrator/`: orchestration, sampling, logging, and
export.
- `src/services/curated_data/`: `CuratedJsonDataService`, the file-backed
`ICuratedDataService`, and `MockCuratedDataService`, the in-memory
`ICuratedDataService` used in `--mocked` runs.

View File

@@ -1,4 +1,12 @@
# Pipeline Roadmap — Reaching the Planned Architecture
---
title: Pipeline roadmap — reaching the planned architecture
last-updated: 2026-08-31
tags:
- pipeline
- roadmap
- cpp
- concurrency
---
This is the engineering breakdown for closing the gap between the **current**
pipeline and the **planned** architecture documented in