*ŚǯŚǯ ¢ ¢ ¢*

 ¢ ¢ Ȭ ¢ ę Śǯŗ ¢ ¢ Ȭ £ ¢ ¢ǯ ¢ ¢ ¢ ǯ


 ŝ ŗDZŗ ŗDZ Ȃ ¢ ¢ ¢ ǯ


 **ŝǯ** ¢Ȯ¢ ¢ ǯ

DZ ¢ ǰ DZ ¢ ǯ -ǯ

#### **śǯ**

 ¢ £ ¢ ¢ 
ǰ ¢ ¢ ¢ǯ ǰ ¢ ¢ ¢ ǯ ¢ ¢ǯ

 £ ¢ ę ę ę ǰ Ĝǰ ǰ ǯǰ ǯ ǰ ǰ ǰ Ĝ ¢ Ĝ Ȃ ǰ ¢

 ǰ Ĵ ę ǯ

 £ ¢ ǯ ¢ £ ¢ ę ¢ Ȭ Ĝǰ ǯ ǰ ¢ ǰ £ £ ¢ ¢ǯ ǰ £ ¢ ¢ ę ¢ ¢ ǯ

 ǰ Ȭ ¢ ¢ǰ £ǰ £ǰ ¢Ȭ ¢ǰ ¢ ¢ ǯ

 **DZ** £ǰ ǯǯ ǯȬǯǯDz ¢ǰ ǯǯ ǯȬǯǯDz Ȭ ǰ ǯǯ ǯȬǯǯDz ¢ǰ ǯǯ ǯȬǯǯDz ǰ ǯǯ ǯȬǯǯDz ǰ ǯǯ ǯȬǯǯDz ȯ ǰ ǯǯ ǯȬǯǯDz ȯ ǰ ǯǯ ǯȬǯǯDz £ǰ ǯǯ ǯȬǯǯDz ǰ ǯǯ ǯȬǯǯDz ǰ ǯǯ ǯȬǯǯDz ǰ ǯȬǯǯ ǯ

**DZ** ¢ ¢ ǻǼ 
 ǰ ¢ ¢ ŘŖŘŗȬŖȬŖŖŗŗŘǯ

 **¢ DZ** ¢ ǯ

**Ě DZ** Ě ǯ

#### 

 ǰ ǯǯDz ǰ ǯDz ǰ ǯ Ȭŗş DZ ¢ǯ *ǯ ǯ* **ŘŖŘŗ**ǰ *ś*ǰ ŗŖŖŖŝŘǯ ǽǾ
ǯDz ǯǰ ǯDz ǯǰ ǯDz ǯǰ ǯDz ǯǰ ǯ DZ ¢ǰ ¢ǰ ǯ *ǯ ǯ* **ŘŖŘŗ**ǰ *ş*ǰ ŘŝŚŚşǯ ǽǾ ǽǾ
ĵǰ ǯ ȯ ǯ *ǯ ǯ ǯ* **ŘŖŘŗ**ǰ *Ŝ*ǰ ŘŘŘȮŘřŗǯ ǽǾ
ǰ ǯ ¢Ȯ ¢ Ȭŗş 
ȯ¢ ǯ *ǯ*  **ŘŖŘŖ**ǰ *řŘř*ǰ ŘŗŘşȮŘŗřŖǯ ǽǾ ǽǾ
ǰ ǯDz ǰ ǯDz ǰ ǯȬǯ Ȭŗş DZ ¢ ¢ ¢ǯ *ǯ ǯ ǯ ǯ* **ŘŖŘŘ**ǰ *ŗş*ǰ řřŘřǯ ǽǾ ǽǾ
 ¢ ¢ǯ Ȭŗş ǯ ŗř ¢ ŘŖŘŘǯ DZ DZȦȦ ǯǯȦȦȦ ȬȬŗşȬ ǻ Řř ŘŖŘŘǼǯ
ǰ ǯDz ǰ ǯDz ǰ ǯǯDz ǰ ǯDz ǰ ǯDz ¢ǰ ǯǯ *DZ ¢Ȭ ¢Ȭ* Dz ¢ ¢DZ ǰ ŘŖŘŖǯ
ǰ ǯǯ Ȭŗş DZ ȁĴȂ ǯ  *ǯ* **ŘŖŘŗ**ǰ *Ş*ǰ ŜşȮŞŝǯ ǽǾ
ǯ DZ DZȦȦǯǯ Ȧ¢ȦȦȦŘŖŘŖȦŖŚȦŘŖŘŖŖŚȬȬŗşȬȬȬ¢ȬȬȬǯ ǻ Řś ŘŖŘŘǼǯ
 ǯ ǯ DZ DZȦȦ ǯ ǯǯȦƖƖŘƖşśƖƖŖƖşȦƖƖŖƖşŖƖƖşŝƖƖƖřƖşŗƖƖşƖşŞ ƖƖşŞƖŞŞƖƖŖƖşƖƖŖƖŞƖƖŚƖŞŖƖƖŜƖƖƖşŝƖşŖƖƖŚƖŞŖƖƖşśƖşƖƖŘƖşśƖ ƖśƖŖ ǻ Řś ŘŖŘŘǼǯ
ǯ
ȬŗŘǯŖřŝŜDZ¢ Ȭ ǯ DZ DZȦȦǯǯǯȦȦȏ ǯǵƽǯȏǭ¢ƽǭ ƽŗǭȏ ƽ
ǯ
ȬŗŘǯŖřŝŜǭȏƽś ǻ Řś ŘŖŘŘǼǯ
 ¢ǯ DZ DZȦȦ ǯǯǯȦǯǵƽŘŖřŖŗŗŗŖŗŖŖ ǻ ŘŞ ŘŖŘŘǼǯ
 ¢ ęǯ DZ DZȦȦ ǯǯȦ Ȧ¢ ǯǵ ƽŗŚŞŞşśŚŖŖǛȬ¢ ǻ Řś ŘŖŘŘǼǯ
ǰ ǯǯ ę Ȭ ££¢ ¢ǯ *ǯ ǯ ǯ ǯ ǯ* **ŘŖŗŝ**ǰ *ś*ǰ ŗřȮŘŖǯ ǽǾ ǽǾ
ǯǰ ǯǯ Ȭ ǯ *ǯ 
 ǯ* **ŘŖŗŝ**ǰ *ŗŝ*ǰ řřȮśŘǯ
 ǯ ǯ DZ DZȦȦ ǯǯǯȦȏȦ ǯǵƽśřŖŚŚǭƽ ǻ ŗś ¢ ŘŖŘŘǼǯ

**Mario A. Leiva 1,2, Alejandro J. García 1,2, Paulo Shakarian <sup>3</sup> and Gerardo I. Simari 1,2,3,\***


**Abstract:** Decision support tools are key components of intelligent sociotechnical systems, and their successful implementation faces a variety of challenges, including the multiplicity of information sources, heterogeneous format, and constant changes. Handling such challenges requires the ability to analyze and process inconsistent and incomplete information with varying degrees of associated uncertainty. Moreover, some domains require the system's outputs to be explainable and interpretable; an example of this is cyberthreat analysis (CTA) in cybersecurity domains. In this paper, we first present the P-DAQAP system, an extension of a recently developed query-answering platform based on defeasible logic programming (DeLP) that incorporates a probabilistic model and focuses on delivering these capabilities. After discussing the details of its design and implementation, and describing how it can be applied in a CTA use case, we report on the results of an empirical evaluation designed to explore the effectiveness and efficiency of a possible world sampling-based approximate query answering approach that addresses the intractability of exact computations.

**Keywords:** intelligent sociotechnical systems; human-in-the-loop computing; structured probabilistic argumentation; cybersecurity
