{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/33444"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/33444","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Usability Evaluation of LLM-Assisted Cross-Platform Migration","abstract":"Large language models are evaluated on whether the code they generate compiles and passes tests. Whether code is usable is a question that has received little attention so far. This thesis asks it in the context of cross-platform mHealth application migration. A sleep-tracking application (React Native, 82 files, 24 screens) was migrated to three frameworks (Kotlin Multiplatform, Flutter, .NET MAUI) by two frontier AI coding agents (Claude Sonnet 4.6, GPT-5.5) under a shared 15-rule prompt. All seven implementations were evaluated by a single assessor on an Android device using Nielsen’s ten heuristics across six standardized tasks. One of six migrations improved on the baseline while five degraded usability. Claude Sonnet 4.6 outperformed GPT-5.5 on every matched framework, but framework choice mattered more than model choice, as declarative UI translated well across all targets while imperative behavioral contracts did not. Both tools independently converged on the same catastrophic failure, suggesting this failure is driven by framework API design rather than by the model itself. The thesis contributes a severity matrix spanning two tools and three frameworks, a reusable heuristic-based evaluation methodology for AI-generated migrations, and a five-type regression taxonomy including modality substitution, a failure mode that existing benchmarks would mark as correct.","abstract_html":"Large language models are evaluated on whether the code they generate compiles and passes tests. Whether code is usable is a question that has received little attention so far. This thesis asks it in the context of cross-platform mHealth application migration. A sleep-tracking application (React Native, 82 files, 24 screens) was migrated to three frameworks (Kotlin Multiplatform, Flutter, .NET MAUI) by two frontier AI coding agents (Claude Sonnet 4.6, GPT-5.5) under a shared 15-rule prompt. All seven implementations were evaluated by a single assessor on an Android device using Nielsen’s ten heuristics across six standardized tasks. One of six migrations improved on the baseline while five degraded usability. Claude Sonnet 4.6 outperformed GPT-5.5 on every matched framework, but framework choice mattered more than model choice, as declarative UI translated well across all targets while imperative behavioral contracts did not. Both tools independently converged on the same catastrophic failure, suggesting this failure is driven by framework API design rather than by the model itself. The thesis contributes a severity matrix spanning two tools and three frameworks, a reusable heuristic-based evaluation methodology for AI-generated migrations, and a five-type regression taxonomy including modality substitution, a failure mode that existing benchmarks would mark as correct.","abstract_has_math":false,"creators":["Mokhtari, Melvin"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Computing and Software","school":null,"contributors":[],"advisors":["Paige, Richard F."],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T19:33:08Z","subjects":["Large Language Models","AI Coding Agents","Cross-Platform Migration","Usability Evaluation","Heuristic Evaluation","mHealth Applications","AI-Generated Code","Usability Regression"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/2228"],"render_values":[{"text":"https://doi.org/10.71548/2228","href":"https://doi.org/10.71548/2228","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/11375/33444","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/11375/33444","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F33444","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Paige, Richard F."]},{"key":"dc:contributor.department","label":"Department","values":["Computing and Software"]},{"key":"dc:creator","label":"Author","values":["Mokhtari, Melvin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-08-11T15:24:46Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Large Language Models","AI Coding Agents","Cross-Platform Migration","Usability Evaluation","Heuristic Evaluation","mHealth Applications","AI-Generated Code","Usability Regression"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/11375/33444","https://doi.org/10.71548/2228"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Large language models are evaluated on whether the code they generate compiles and passes tests. Whether code is usable is a question that has received little attention so far. This thesis asks it in the context of cross-platform mHealth application migration. A sleep-tracking application (React Native, 82 files, 24 screens) was migrated to three frameworks (Kotlin Multiplatform, Flutter, .NET MAUI) by two frontier AI coding agents (Claude Sonnet 4.6, GPT-5.5) under a shared 15-rule prompt. All seven implementations were evaluated by a single assessor on an Android device using Nielsen’s ten heuristics across six standardized tasks. One of six migrations improved on the baseline while five degraded usability. Claude Sonnet 4.6 outperformed GPT-5.5 on every matched framework, but framework choice mattered more than model choice, as declarative UI translated well across all targets while imperative behavioral contracts did not. Both tools independently converged on the same catastrophic failure, suggesting this failure is driven by framework API design rather than by the model itself. The thesis contributes a severity matrix spanning two tools and three frameworks, a reusable heuristic-based evaluation methodology for AI-generated migrations, and a five-type regression taxonomy including modality substitution, a failure mode that existing benchmarks would mark as correct."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science (MSc)"]},{"key":"dc:title","label":"Title","values":["Usability Evaluation of LLM-Assisted Cross-Platform Migration"]},{"key":"dc:title.alternative","label":"Alternative Title","values":["\"Who Moved My Button?'': A Usability Evaluation of LLM-Assisted Cross-Platform Migration"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Paige, Richard F."],"dc:contributor.department":["Computing and Software"],"dc:creator":["Mokhtari, Melvin"],"dc:date.accessioned":["2026-08-11T15:24:46Z"],"dc:date.issued":["2026"],"dc:description.abstract":["Large language models are evaluated on whether the code they generate compiles and passes tests. Whether code is usable is a question that has received little attention so far. This thesis asks it in the context of cross-platform mHealth application migration. A sleep-tracking application (React Native, 82 files, 24 screens) was migrated to three frameworks (Kotlin Multiplatform, Flutter, .NET MAUI) by two frontier AI coding agents (Claude Sonnet 4.6, GPT-5.5) under a shared 15-rule prompt. All seven implementations were evaluated by a single assessor on an Android device using Nielsen’s ten heuristics across six standardized tasks. One of six migrations improved on the baseline while five degraded usability. Claude Sonnet 4.6 outperformed GPT-5.5 on every matched framework, but framework choice mattered more than model choice, as declarative UI translated well across all targets while imperative behavioral contracts did not. Both tools independently converged on the same catastrophic failure, suggesting this failure is driven by framework API design rather than by the model itself. The thesis contributes a severity matrix spanning two tools and three frameworks, a reusable heuristic-based evaluation methodology for AI-generated migrations, and a five-type regression taxonomy including modality substitution, a failure mode that existing benchmarks would mark as correct."],"dc:description.degree":["Master of Science (MSc)"],"dc:identifier.uri":["https://hdl.handle.net/11375/33444","https://doi.org/10.71548/2228"],"dc:language.iso":["en"],"dc:subject":["Large Language Models","AI Coding Agents","Cross-Platform Migration","Usability Evaluation","Heuristic Evaluation","mHealth Applications","AI-Generated Code","Usability Regression"],"dc:title":["Usability Evaluation of LLM-Assisted Cross-Platform Migration"],"dc:title.alternative":["\"Who Moved My Button?'': A Usability Evaluation of LLM-Assisted Cross-Platform Migration"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:33:08Z"}