34.1 MB

Ctrl+K

1 contributor

History: 10 commits

anxuanng

Gate chart: one-line note

5fd9805 verified 4 days ago

charts
Gate chart: one-line note 4 days ago
charts_web
Gate chart: one-line note 4 days ago
read_v2
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
reports
Gate chart: one-line note 4 days ago
.gitattributes

1.94 kB
Redrawn charts: Inter, fewer labels, one number per chart 4 days ago
LICENSE

10.8 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
README.md

10.7 kB
Gate chart: one-line note 4 days ago
benchmark.py

16.6 kB
Gate chart: one-line note 4 days ago
block_maps.json

9.93 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
block_measure.py

7.38 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
collect_page.cjs

23.8 kB
Gate chart: one-line note 4 days ago
demo.mp4

29.2 MB
xet

Loupe research preview: audit code, read weights, benchmark reports 4 days ago
evaluate_fresh.py

5.78 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
evaluate_generalisation.py

16 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
external_design2code.py

8.76 kB
Add the Design2Code human-judged benchmark: Loupe does not beat a pixel baseline there 4 days ago
external_design2code_sonnet.py

5.63 kB
Gate chart: one-line note 4 days ago
fit_multi_line.py

3.97 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
group_checks.py

6.72 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
loupe.py

3.02 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
multi_line.json

458 Bytes
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
page_audit.py

22.7 kB
Gate chart: one-line note 4 days ago
pixel_measurements.py

5.87 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
read_runtime.py

8.39 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
rule_checks.py

16.5 kB
Gate chart: one-line note 4 days ago
sensitivity.py

4.05 kB
More benchmarks: eight windows per fault against Sonnet, fault size test, speed, charts 4 days ago
similarity.py

7.35 kB
Continuous similarity: 76.4 percent agreement with human judges on held-out Design2Code pairs 4 days ago
text_cache.pt

42.6 kB
xet

Loupe research preview: audit code, read weights, benchmark reports 4 days ago
timing.py

2.43 kB
More benchmarks: eight windows per fault against Sonnet, fault size test, speed, charts 4 days ago
tolerances.json

229 Bytes
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
trusted_checks.json

292 Bytes
Loupe research preview: audit code, read weights, benchmark reports 4 days ago
validate_page_measures.py

3.25 kB
Loupe research preview: audit code, read weights, benchmark reports 4 days ago