Davis Brown

davisrbr's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 1 day ago

davisrbr/openconjecture

Preview • Updated 1 day ago • 252 • 9

liked a dataset 4 days ago

davisrbr/openconjecture

Preview • Updated 1 day ago • 252 • 9

New activity in steinad/CheatBench 6 days ago

Add per-row localization fields (loc_kind, loc_field_path, loc_line_start/end, loc_snippet, ...)

#3 opened 6 days ago by

davisrbr

New activity in steinad/CheatBench 10 days ago

Add round-2 benchmarks: mle-bench (150) + kernelbench (36) + swe-rebench (48)

1

#2 opened 10 days ago by

davisrbr

published 2 datasets about 2 months ago

BrachioLab/dist-defense-traces-multicampaign-main100-augbenign-anchors-eval-v3-artemis-turnlike

Viewer • Updated Mar 2 • 360k • 6

davisrbr/openconjecture

Preview • Updated 1 day ago • 252 • 9

published 2 datasets 2 months ago

BrachioLab/jailbreak_harmbench50

Viewer • Updated May 22, 2025 • 857 • 270

BrachioLab/forecasting_100_adaptive

Viewer • Updated May 22, 2025 • 1.39k • 60

updated a dataset 2 months ago

BrachioLab/dist-defense-traces-multicampaign-main100-augbenign-anchors-eval-v3-artemis-turnlike

Viewer • Updated Mar 2 • 360k • 6

published 2 datasets 3 months ago

BrachioLab/truthfulqa_generated_questions

Viewer • Updated May 22, 2025 • 1.35k • 6

BrachioLab/cyberbullying_jailbreak

Viewer • Updated May 22, 2025 • 500 • 11

updated a collection 3 months ago

Adaptive Evaluations

Collection

Datasets for our paper, Adaptively profiling models with task elicitation (EMNLP 2025). • 6 items • Updated Feb 16

updated a dataset 3 months ago

BrachioLab/dist-defense-traces-taskname-split-augmented-plus-synth-v15

Viewer • Updated Feb 12 • 367k • 25

published a dataset 3 months ago

BrachioLab/dist-defense-traces-taskname-split-augmented-plus-synth-v15

Viewer • Updated Feb 12 • 367k • 25

updated a dataset 3 months ago

BrachioLab/dist-defense-traces-augmented-taskname-split

Viewer • Updated Feb 12 • 331k • 11

published a dataset 4 months ago

BrachioLab/dist-defense-traces-augmented-taskname-split

Viewer • Updated Feb 12 • 331k • 11