EMMANUEL NWANGUMA

Emar7's activity

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

New activity in Station-house/ConspiracyBench 3 days ago

Baseline requirements and a pre run check for valid runs

2

#124 opened 5 days ago by

pluuto19

Add leading and adversarial WTC 7 framings (claim_id wtc7-fire-induced-collapse)

4

#158 opened 3 days ago by

Emar7

Proposal: human-in-the-loop pipeline for drafting candidate questions (dataset workstream)

12

#61 opened 12 days ago by

newsss

write question files as UTF-8 in scripts/

6

#88 opened 7 days ago by

gowrishkumar

New activity in Station-house/ConspiracyBench 7 days ago

Add question: Khufu pyramid builders

6

#77 opened 9 days ago by

melover24

Add a context budget checked before each model and judge call

1

#87 opened 7 days ago by

Emar7

New activity in Station-house/ConspiracyBench 8 days ago

Windows encoding bug in scripts

2

#84 opened 8 days ago by

gowrishkumar

New activity in Station-house/ConspiracyBench 10 days ago

Inspect solver and scorer infrastructure: repeated sampling, metrics, report

2

#68 opened 11 days ago by

stationhouse

New activity in Station-house/ConspiracyBench 13 days ago

Add an Inspect pilot of ConspiracyBench in inspect_eval/

1

#54 opened 13 days ago by

Emar7

New activity in Station-house/ConspiracyBench 14 days ago

Add optional region and language metadata

4

#53 opened 14 days ago by

anushka1409

Transition the overall tech stack to AISI Inspect framework, or any other off the shelf tooling?

8

#42 opened 17 days ago by

JoyeeChen

New activity in Station-house/ConspiracyBench 15 days ago

Add multi-turn question: MMR and autism

5

#41 opened 17 days ago by

Emar7

Add question: WTC 7 collapse

6

#18 opened 21 days ago by

Emar7

schema.json is out of sync with SCHEMA.md

3

#28 opened 21 days ago by

newsss

Add multi-turn 5G and COVID-19 question

4

#51 opened 16 days ago by

melover24

Restore claim_id in schema.json (dropped by #39)

1

#52 opened 15 days ago by

Emar7

liked a model 16 days ago

Emar7/phi4-finance-finetuned

Text Generation • Updated Mar 3 • 30 • 2

New activity in Station-house/ConspiracyBench 16 days ago

Add multi-turn judge regression cases

1

#44 opened 16 days ago by

Emar7

Rename the 9-11 category to terrorism

👍 1

1

#39 opened 17 days ago by

stationhouse

Add questions: conspiracy questions popular in india and south east asia

2

#31 opened 20 days ago by

vaisakhi