A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
hub Canonical reference
Artif Intell345, 104346 (2025)
Canonical reference. 80% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
years
2026 12roles
background 5representative citing papers
Backtrackable Inprocessing enables sound inprocessing at arbitrary decision levels in incremental SAT solving and solves about 1.5 times as many difficult bounds on 2017 BMC benchmarks compared to global-level preprocessing.
Online policies achieve optimal fairness of 1/(1+R_beta) for arbitrary arrivals and a tighter [1-(1-R_beta/T)^T]/R_beta bound for stationary arrivals via the RCB algorithm, with partial fulfillment required for optimality.
N-DCA distributes coalition value calculations via a bijection to two-colour combinatorial necklaces and increment arrays, achieving no-communication equitable allocation with tight load-balance guarantees and self-interest.
Introduces parallelizable, theory-agnostic methods for complete theory-lemma enumeration in SMT that scale better than classic eager encodings on complex instances.
A hybrid recommender system combining metadata-driven similarity and matrix completion recommends closure models for new multiphase flow CFD cases and reduces performance regret relative to baselines on 136 validation cases.
A method that translates causal relationships into a Bipolar Argumentation Framework and applies semi-stable semantics to generate explanatory feature sets for machine learning predictions.
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
NSFL adapts t-norms and t-conorms to embedding spaces with NS-Delta and SQO to enable logical operations, reporting up to 81% mAP gains in retrieval tasks.
A neurosymbolic pipeline extracts predicates from offer texts with an LLM and validates them via Logic Tensor Networks, delivering performance comparable to standard models plus built-in interpretability on a real corpus.
citing papers explorer
-
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
-
Backtrackable Inprocessing
Backtrackable Inprocessing enables sound inprocessing at arbitrary decision levels in incremental SAT solving and solves about 1.5 times as many difficult bounds on 2017 BMC benchmarks compared to global-level preprocessing.
-
Promoting Fair Online Resource Allocation with Indivisible Units
Online policies achieve optimal fairness of 1/(1+R_beta) for arbitrary arrivals and a tighter [1-(1-R_beta/T)^T]/R_beta bound for stationary arrivals via the RCB algorithm, with partial fulfillment required for optimality.
-
From Necklaces to Coalitions: Fair and Self-Interested Distribution of Coalition Value Calculations
N-DCA distributes coalition value calculations via a bijection to two-colour combinatorial necklaces and increment arrays, achieving no-communication equitable allocation with tight load-balance guarantees and self-interest.
-
Beyond Eager Encodings: A Theory-Agnostic Approach to Theory-Lemma Enumeration in SMT
Introduces parallelizable, theory-agnostic methods for complete theory-lemma enumeration in SMT that scale better than classic eager encodings on complex instances.
-
Hybrid Cold-Start Recommender System for Closure Model Selection in Multiphase Flow Simulations
A hybrid recommender system combining metadata-driven similarity and matrix completion recommends closure models for new multiphase flow CFD cases and reduces performance regret relative to baselines on 136 validation cases.
-
A Causal Argumentation Method for Explainability of Machine Learning Models
A method that translates causal relationships into a Bipolar Argumentation Framework and applies semi-stable semantics to generate explanatory feature sets for machine learning predictions.
-
Position: AI as Part of Self -- Extending the Mind Requires Cognitive Co-Regulation
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
-
NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings
NSFL adapts t-norms and t-conorms to embedding spaces with NS-Delta and SQO to enable logical operations, reporting up to 81% mAP gains in retrieval tasks.
-
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
A neurosymbolic pipeline extracts predicates from offer texts with an LLM and validates them via Logic Tensor Networks, delivering performance comparable to standard models plus built-in interpretability on a real corpus.
- Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions