The Math-Aware Retrieval benchmark from MathNet (paper): given an Olympiad problem, retrieve a mathematically equivalent reformulation of it from a large corpus of hard negatives. Each equivalent is provided at three difficulty tiers — easy, medium, hard — that increasingly disguise the surface form while preserving the underlying problem, so retrieval gets sharply harder even though the answer is the same. - 15,000 queries, one gold-equivalent target per tier. - 3 tiers (easy, medium, hard), over a shared 117,088-doc corpus (equivalents at all tiers + LLM near-miss hard negatives + distractors). - Standard BEIR / MTEB layout. All three configs share the same corpus and queries; they differ…
Independent publisher
Shaden
ShadenA
Representation Learning, Reasoning, Vision Language Models
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers8
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text retrieval.
Reported licenses: cc-by-4.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.