Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
# Volume data (downloaded via setup_data.py)
data/volumes/

# Render cache (regenerated from volumes; can reach hundreds of MB)
data/cache/

# Filmstrip viewer (generated by make_filmstrip.py)
data/filmstrip/

Expand Down
17 changes: 17 additions & 0 deletions MIGRATION_REPORT.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Migration Report — Phase B live re-baseline

Generated by `validate_migration.py`. Stages: 1.5fold+2fold+pretzel, n=233 frames (embryos 1–3).

## Leaderboard (new harness)

| Variant | Model | Thinking | mean ± std | N | vs archived |
|---|---|---|---|---|---|
| hybrid | claude-opus-4-6 | none | 80.1 ± 4.2 | 3 | 81.7±2.4 (t=-0.63) ✓ |
| hybrid | claude-opus-4-6 | adaptive | 77.8 ± 1.2 | 3 | — |
| hybrid | claude-opus-4-7 | none | 57.1 ± 2.4 | 3 | — |
| hybrid | claude-opus-4-7 | adaptive | 53.1 ± 9.5 | 3 | — |

## Pass criteria

- **No accuracy regression**: hybrid@opus-4-6/none mean within [77, 86] (81.7 ± 2σ from RESEARCH.md).
- **Provenance**: every result JSON has full config (model, thinking, git_sha, seed) — verified by construction.
Loading