atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Strong Explanations in Abstract Argumentation

AAAI 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Counterfactual explanations and recourse · 16 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use strong explanations instead of requiring an extension itself to serve as the explanationCredulous acceptance in abstract argumentation frameworks · AFs under the considered semanticsexplanation sizeHelped
Require an explanation to preserve acceptance in every subframework containing itStrong explanation verification under grounded semantics · VER-EXPLgrcomplexity: in P -> coNP-completeHurt
Require an explanation to preserve acceptance in every subframework containing itStrong explanation verification under admissible, complete, stable, and preferred semantics · VER-EXPLσcomplexity: in P -> Πp2-cHurt
Require a strong explanation to be subset-minimalStrong grounded explanations · VER-MIN-EXPLgrcomplexity: in P -> Dp1-cHurt
Require a strong explanation to be subset-minimalStrong explanations under admissible, complete, stable, and preferred semantics · VER-MIN-EXPLσcomplexity: in P or coNP-c -> Dp2-cHurt
Use the grounded explanation when the target set is contained in the grounded extensionStrong explanations under grounded, admissible, complete, or preferred semantics · AFs where X is in the grounded extensionconstruction time complexityHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy