OptRecover is a dataset for conversational specification recovery in optimization modeling. Given an incomplete problem description, an assistant asks clarification questions and combines the answers into a recovered specification. Structured references support controlled answering and evaluation of how much missing information has been recovered. The dataset covers 12 scenario families, including task assignment, staff scheduling, logistics, healthcare, admissions, and team formation. All problem descriptions are in English. The dataset contains 48 complete problems and 288 incomplete variants, with a structured reference for every description. Each complete problem has six variants: two…
Independent publisher
OptRecover
OptRecover
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
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.
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.