datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
insight-ladder-imo2024
Insight Ladder - IMO 2024 Hint-Annotated Diagnostic Substrate
Supplementary dataset for "The Insight Ladder: Quantifying the Search-Execution Gap in LLM Mathematical Reasoning" (NeurIPS 2026 Evaluations & Datasets Track, double-blind submission).
Overview
A high-density diagnostic substrate for studying search failure vs execution failure in LLM mathematical proof generation. Covers 31 IMO 2024 Shortlist problems with:
4-level hint hierarchy (L1 domain, L2 first step, L3… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-insightladder-2026/insight-ladder-imo2024.srs-prompts
SRS Prompts
srs-prompts is a collection of highlight-anchored memory prompts, each paired with its highlight, source context, and a tier label (T0–T3).
See the Memory Machines appendix for details on the dataset, including the taxonomy, collection methodology, and schema. A companion dataset, laddermedia/srs-highlights, aggregates these prompts back to the highlight level.