On the full propositional logic dataset, LLM-found bug fixing transformations explain 84.44% of pairs versus 71.57% for hand-picked mistakes¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? On the full propositional dataset of 6106 pairs, workflow-found transformations explain 5156 pairs (84.44%) while hand-picked mistakes explain 4370 pairs (71.57%), with 918 pairs (15.03%) explained exclusively by the transformations. → Lilian Killich 2026
Evidence¶
Lilian Killich 2026¶
Lilian Killich, Marko Schmellenkamp, Fabian Vehlken, Thomas Zeume. (2026). Finding Common Mistakes In Modelling With Mathematical Formalisms Using LLMs. https://arxiv.org/abs/2609.17111 doi:10.48550/arxiv.2609.17111
q2 · i? · design · r2
Evaluation on the propositional logic dataset from prior work (6106 pairs, 1572 distinct), comparing coverage of workflow-found transformations against hand-picked mistakes; the transformations "explain 5156 of the pairs (84.44%)" versus 71.57% for hand-picked mistakes. No effect size is printed.
"Across the whole data set, the bug fixing transformations found by our workflow explain 5156 of the pairs (84.44%), whereas the hand-picked mistakes only explain 4370 of the pairs (71.57%). 918 pairs (15.03%) are exclusively explained by the transformations"
Discussion¶
Related Claims¶
- Educator inspection found most large clusters' main transformations suitable for feedback, though many required sub-transformations for targeted feedback — related
- Across linguistic-operator subdatasets, workflow-found transformations explain at least as many pairs as hand-picked mistakes in most cases — related
- The workflow discovers new mistake candidates not explained by prior hand-picked mistakes, such as an exclusive-or-instead-of-negated-conjunction mistake — a narrower finding that bears on this claim
- The workflow generalizes beyond propositional logic, explaining 79.39% of modal logic pairs and 35.89% of CTL pairs — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llm-transformations-explain-more-propositional-pairs-than-hand-picked |
title |
On the full propositional logic dataset, LLM-found bug fixing transformations explain 84.44% of pairs versus 71.57% for hand-picked mistakes |
description |
On the full propositional logic dataset, LLM-found bug fixing transformations explain 84.44% of pairs versus 71.57% for hand-picked mistakes |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — lilian-killich-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.