{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T10:44:38Z","timestamp":1771843478339,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains which directly affect human well-being. However, if AI is to improve people\u2019s lives, then\npeople must be able to trust it, by being able to understand what the system is doing and why. Although transparency is often seen as the requirement in this case, realistically it might not always\nbe possible, whereas the need to ensure that the system operates within set moral bounds remains. \nIn this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a \u2018Glass-Box\u2019 around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems.\nThe explicit transformation of abstract moral values into concrete norms brings great benefits in terms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/802","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"5787-5793","source":"Crossref","is-referenced-by-count":14,"title":["Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour"],"prefix":"10.24963","author":[{"given":"Andrea","family":"Aler Tubella","sequence":"first","affiliation":[{"name":"Ume\u00e5 University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Theodorou","sequence":"additional","affiliation":[{"name":"Ume\u00e5 University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Dignum","sequence":"additional","affiliation":[{"name":"Ume\u00e5 University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Virginia","family":"Dignum","sequence":"additional","affiliation":[{"name":"Ume\u00e5 University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:51:55Z","timestamp":1564300315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/802"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/802","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}