AI Paper Atlas

Research map / Large language models / Agents, code and math

HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds

Tingting Chen, Beibei Lin, Zifeng Yuan, Qiran Zou, Hongyu He, Anirudh Goyal, Yew-Soon Ong, Dianbo Liu

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase admissible set size from level 1 to level 3frontier LLMs · DNA Interaction (GPT-5)RR: 100.00% -> 48.00%Hurt
increase admissible set to |H_O|=160GPT-5 · Causal InferenceNR/RR: 100.0% -> 71.2% (RR)Hurt
increase admissible set to |H_O|=125Grok-4 · 3D voxelRR: 79.2% (VR 100.0%)Hurt
use reasoning models rather than non-reasoning modelsLLMs · Causal level 3RR: 99.20% vs 6.70% (GPT-5 vs GPT-4o)Improved
add complexity-stratified decodingGrok-4 · Boolean, complex hypothesesRR: 0% -> 17.2%Improved
add complexity-stratified decodingDeepSeek-R1 · Boolean overall RRRR: 25.6% -> 6.4%Hurt
add complexity-stratified decodingGPT-5 · Boolean simple hypothesesRR: -14.3 points (simple)Hurt
add complexity-stratified decoding7 LLMs · Boolean genetic interactionsoverall RR: improves 4/7 modelsMixed
vary temperature and top-p (ablation)GPT-4o, Claude-Opus-4, Gemini-2.5-Pro · Boolean (Hard)RRNo clear effect
increase sampling budget to 3.0x|H_O| (ablation)Gemini-2.5-Pro · Boolean (Hard)RR: -9.9Hurt
increase sampling budget to 3.0x|H_O| (ablation)Claude-Opus-4 · Boolean (Hard)RR: +1.8No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy