Search arXiv⌕ Search

arXiv subjects

Esdras Medeiros

Publications and source records attributed to Esdras Medeiros.

2 recordsLinked to original sources

ProofDiff: Auditable Argument-Level Comparison of AI-Generated Mathematical Proofs

Mathematical understanding depends on the route from hypotheses to conclusion: how the parts of a proof function and which dependencies carry the argument forward. This structure can persist when wording or notation changes, while a small alteration to a hypothesis or inference can produce a different argument beneath similar prose. Formal verification can establish that a rewrite proves the same theorem, but not whether it follows the same mathematical route. Comparing informal proofs, especially those produced or revised by generative models, therefore requires reconstructing which claims, dependencies, and reasoning steps are preserved, reorganized, or replaced. We present ProofDiff, a system for comparing informal mathematical documents. It is designed to support human review, not to certify mathematical correctness. Given two documents, ProofDiff independently constructs a source-grounded argument map for each and proposes correspondences between the resulting maps. Each map captures the document's claims and reasoning steps and records the typed relations that connect them. An integrated human-review layer allows reviewers to revise the maps and correspondences while preserving an auditable history. Comparing the two argument maps provides a basis for inspecting whether the documents follow the same mathematical route and where their claims or dependencies differ. We demonstrate ProofDiff on four illustrative pairs of AI-generated proofs, ranging from a detailed proof and its concise revision to proofs using different mathematical strategies.

cs.AI↗

Visualizing and Understanding Large-Scale Assessments in Mathematics through Dimensionality Reduction

In this paper, we apply the Logistic PCA (LPCA) as a dimensionality reduction tool for visualizing patterns and characterizing the relevance of mathematics abilities from a given population measured by a large-scale assessment. We establish an equivalence of parameters between LPCA, Inner Product Representation (IPR) and the two paramenter logistic model (2PL) from the Item Response Theory (IRT). This equivalence provides three complemetary ways of looking at data that assists professionals in education to perform in-context interpretations. Particularly, we analyse the data collected from SPAECE, a large-scale assessment in Mathematics that has been applied yearly in the public educational system of the state of Ceará, Brazil. As the main result, we show that the the poor performance of examinees in the end of middle school is primarily caused by their disabilities in number sense.

stat.AP↗