[claude] Eval harness results as 3D bar chart (#283) #322

claude · 2026-03-24T04:58:17Z

claude commented

2026-03-24 04:58:17 +00:00

Fixes #283

Adds a holographic 3D bar chart floating beside the Nexus platform showing eval harness metrics — baseline vs fine-tuned model performance.

Changes:

eval-results.json: data file with 5 metrics (accuracy, F1, BLEU, recall, precision)
buildEvalBarChart(): BoxGeometry bars (blue=baseline, green=fine-tuned) with edge glow, y-axis gridlines at 25/50/75/100%, metric labels, title banner, colour legend — all via canvas textures matching the holographic aesthetic
loadEvalResults(): fetches eval-results.json, falls back to inline stub
Gentle vertical float animation in the main animate() loop
Ambient PointLight inside chart group for atmosphere
Chart positioned at (13, 1.5, -4) rotated to face the platform

Fixes #283 Adds a holographic 3D bar chart floating beside the Nexus platform showing eval harness metrics — baseline vs fine-tuned model performance. **Changes:** - `eval-results.json`: data file with 5 metrics (accuracy, F1, BLEU, recall, precision) - `buildEvalBarChart()`: BoxGeometry bars (blue=baseline, green=fine-tuned) with edge glow, y-axis gridlines at 25/50/75/100%, metric labels, title banner, colour legend — all via canvas textures matching the holographic aesthetic - `loadEvalResults()`: fetches `eval-results.json`, falls back to inline stub - Gentle vertical float animation in the main `animate()` loop - Ambient PointLight inside chart group for atmosphere - Chart positioned at (13, 1.5, -4) rotated to face the platform

claude added 1 commit 2026-03-24 04:58:19 +00:00

feat: eval harness results as 3D bar chart — baseline vs fine-tuned (#283 )

CI / validate (pull_request) Failing after 7s

Details

CI / auto-merge (pull_request) Has been skipped

Details

25cca98636

Adds a holographic 3D bar chart floating beside the platform showing
eval harness metrics comparing baseline vs fine-tuned model performance.

- eval-results.json: data file with 5 metrics (accuracy, F1, BLEU,
  recall, precision) for baseline and fine-tuned model scores
- buildEvalBarChart(): constructs BoxGeometry bars (blue=baseline,
  green=fine-tuned) with edge glow, y-axis gridlines, metric labels,
  title banner, and colour legend using canvas textures
- loadEvalResults(): fetches eval-results.json, falls back to stub
- Gentle vertical float animation in the main animate loop
- Glow PointLight inside chart group for ambient atmosphere

Fixes #283

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

groq referenced this pull request

2026-03-24 04:58:23 +00:00

Research: NotebookLM — create audio overview of SOUL.md as podcast #293

claude referenced this pull request

2026-03-24 04:58:30 +00:00

Eval harness results as 3D bar chart — baseline vs fine-tuned #283

groq referenced this pull request

2026-03-24 04:59:37 +00:00

Research: NotebookLM — create audio overview of SOUL.md as podcast #293

Timmy closed this pull request

2026-03-24 12:35:11 +00:00

allegro referenced this pull request