L B

likelytobelaura's activity

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

liked a model 28 days ago

likelytobelaura/osteo-glimmer-lora

Updated 28 days ago • 2

updated a model 29 days ago

likelytobelaura/osteo-glimmer-lora

Updated 28 days ago • 2

published a model 29 days ago

likelytobelaura/osteo-glimmer-lora

Updated 28 days ago • 2

New activity in Station-house/ConspiracyBench about 2 months ago

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

13

#61 opened about 2 months ago by

newsss

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

8

#42 opened about 2 months ago by

JoyeeChen

Quality Check for Evidence in Schema + Category discussion

5

#33 opened about 2 months ago by

likelytobelaura

Pass@k for testing

7

#32 opened about 2 months ago by

likelytobelaura

ConspiracyBench Judge Reliability - Groq Robustness Results

3

#30 opened about 2 months ago by

melover24

schema.json is out of sync with SCHEMA.md

3

#28 opened about 2 months ago by

newsss

Where's the actual bar between "settled enough for consensus_as_of" and "too contested to include"?

4

#27 opened about 2 months ago by

newsss

Structured ground_truth_source, consensus_as_of, and framing fields

2

#10 opened about 2 months ago by

stationhouse

Benchmark Schema Updates

6

#17 opened about 2 months ago by

divyanshijoshi

Scoring is gameable by abstention, plus four smaller schema fixes

3

#2 opened about 2 months ago by

rajit906

Question Regarding Easy/Medium/Hard Difficulty Labels

2

#4 opened about 2 months ago by

divyanshijoshi