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. |
||
|---|---|---|
| .. | ||
| 10dlc-isv-setup-guide.haiku.md | ||
| 10dlc-isv-setup-guide.opus.md | ||
| 10dlc-isv-setup-guide.sonnet.md | ||
| README.md | ||
| ai-coding-conventions-synthesis.haiku.md | ||
| ai-coding-conventions-synthesis.opus.md | ||
| ai-coding-conventions-synthesis.sonnet.md | ||
| oo-principles-plugin-concept.haiku.md | ||
| oo-principles-plugin-concept.opus.md | ||
| oo-principles-plugin-concept.sonnet.md | ||
| pest-control-email-abc-hub.haiku.md | ||
| pest-control-email-abc-hub.opus.md | ||
| pest-control-email-abc-hub.sonnet.md | ||
| pest-control-enterprise-revenue.haiku.md | ||
| pest-control-enterprise-revenue.opus.md | ||
| pest-control-enterprise-revenue.sonnet.md | ||
| pest-control-sms-market-research-stats.haiku.md | ||
| pest-control-sms-market-research-stats.opus.md | ||
| pest-control-sms-market-research-stats.sonnet.md | ||
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.