cc-os/docs/memory-system/benchmark/reference-outputs
jared 77355b4b44 Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs
Completed the benchmark run that gates Ollama model selection. Generated 18
reference fragments (6 cross-domain fixtures × 3 Claude tiers) and tightened
extraction spec rules based on first-run learnings. Updated implementation
status to reflect that reference set is complete and Ollama scoring is
unblocked. Populated fixture list in dispatch-prompt with final selection.
2026-06-04 12:49:22 -04:00
..
10dlc-isv-setup-guide.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
10dlc-isv-setup-guide.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
10dlc-isv-setup-guide.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
README.md Add incremental-migration + reference-benchmark change (ADR-013) 2026-06-04 11:17:32 -04:00
ai-coding-conventions-synthesis.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
ai-coding-conventions-synthesis.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
ai-coding-conventions-synthesis.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
oo-principles-plugin-concept.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
oo-principles-plugin-concept.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
oo-principles-plugin-concept.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-email-abc-hub.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-email-abc-hub.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-email-abc-hub.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-enterprise-revenue.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-enterprise-revenue.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-enterprise-revenue.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-sms-market-research-stats.haiku.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-sms-market-research-stats.opus.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00
pest-control-sms-market-research-stats.sonnet.md Execute Step 2c: Claude reference-set benchmark — 18 gold-standard outputs 2026-06-04 12:49:22 -04:00

README.md

Reference Outputs

Last updated: 2026-06-04

This directory holds the per-model Graphify-shaped extraction fragments generated by the Claude-tier reference-set benchmark (see ../dispatch-prompt.md).

File naming convention

<note-slug>.<tier>.md

Where:

  • <note-slug> is the kebab-case identifier for the fixture note (assigned in Step 1c of the build runbook)
  • <tier> is one of: haiku, sonnet, opus

Contents

Each file contains the YAML extraction fragment for one fixture note as produced by one Claude tier. Files are generated by running the dispatch prompt — they do not exist until that step is executed.

claude-opus-4-8's .opus.md files are the gold-standard rubric against which local Ollama doc-extraction models are scored in a later step.