EMMANUEL NWANGUMA

Emar7's activity

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

New activity in Station-house/ConspiracyBench 5 days ago

Which conspiracy theories do models endorse in all 5 tries?

5

#447 opened 9 days ago by

PMoeller

Analysis: cross-eval verdict agreement

5

#451 opened 7 days ago by

vivekp0108

New activity in Station-house/ConspiracyBench 16 days ago

Expand abiola-poisoned-1998: leading and adversarial framings

1

#427 opened 16 days ago by

Emar7

New activity in Station-house/ConspiracyBench 17 days ago

Add question: 2017 "vampire" rumours in Malawi (medium, Africa)

1

#425 opened 17 days ago by

Emar7

[TOP PRIORITY] Make model outputs more deterministic or find stronger judge models

3

#407 opened 21 days ago by

stationhouse

Add question: Bofors Scandal Legal Findings

4

#375 opened 23 days ago by

pranavdarshan

New activity in Station-house/ConspiracyBench 23 days ago

Add question: WHO "$20m bribe" claim about Covid-Organics (hard, Africa)

1

#371 opened 23 days ago by

Emar7

Judge Selection

5

#370 opened 24 days ago by

stationhouse

New activity in Station-house/ConspiracyBench 27 days ago

Add pressure turns to Princess Diana question (cb-0006)

6

#172 opened about 1 month ago by

CanadianResearcherAnji

Add question: Abiola's death in 1998 (hard, Africa)

#255 opened 27 days ago by

Emar7

Task Thread: Choosing the judge: a decision protocol, the real-transcript gap, and a poll plan

30

#203 opened about 1 month ago by

powercoding1

updated a model 28 days ago

Emar7/N-ATLaS-Health-QA-LoRA-Powered-by-Awarri

Updated 27 days ago • 35

published a model 28 days ago

Emar7/N-ATLaS-Health-QA-LoRA-Powered-by-Awarri

Updated 27 days ago • 35

liked a model 28 days ago

NCAIR1/N-ATLaS

8B • Updated Sep 23, 2025 • 5.11k • 212

New activity in Station-house/ConspiracyBench about 1 month ago

Judge parser: a negated label is not a verdict

4

#183 opened about 1 month ago by

powercoding1

Add question: Nigeria "plastic rice" seizure, 2016 (hard, adversarial, Africa)

#202 opened about 1 month ago by

Emar7

Add question: Buhari body-double claim (medium, Africa)

#201 opened about 1 month ago by

Emar7

Score cut-off replies invalid and report invalid turns by reason

1

#200 opened about 1 month ago by

Emar7

Task Thread: "How reliable is the scorer infrastructure?": proposed bar and plan

6

#182 opened about 1 month ago by

powercoding1

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

5

#158 opened about 1 month ago by

Emar7