{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/euca-dataset","name":"EUCA dataset","full_name":null,"description_markdown":"# EUCA dataset description\r\n\r\nAssociated Paper: \r\n**[EUCA: the End-User-Centered Explainable AI Framework](http://arxiv.org/abs/2102.02437)**\r\n\r\nAuthors:\r\nWeina Jin, Jianyu Fan, Diane Gromala, Philippe Pasquier, Ghassan Hamarneh\r\n\r\n## Introduction:\r\n\r\nEUCA dataset is for modelling personalized or interactive explainable AI. It contains 309 data points of 32 end-users' preferences on 12 forms of explanation (including feature-, example-, and rule-based explanations). The data were collected from a user study on 32 layperson participants in the Greater Vancouver city area in 2019-2020. In the user study, the participants (P01-P32) were presented with AI-assisted critical tasks on house price prediction, health status prediction, purchasing a self-driving car, and studying for a biological exam [1]. Within each task and for its given explanation goal [2], the participants selected and rank the explanatory forms [3] that they saw the most suitable. \r\n\r\n1 [EUCA_EndUserXAI_ExplanatoryFormRanking.csv](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/EUCA_EndUserXAI_ExplanatoryFormRanking.csv)\r\n\r\n   **Column description**:\r\n\r\n   - **Index** - Participants' number\r\n   - **Case** - task-explanation goal combination\r\n   - **accept to use AI? trust it?** - Participants response to whether they will use AI given the task and explanation goal\r\n   - **require explanation?** - Participants response to the question whether they request an explanation for the AI\r\n   - **1st, 2nd, 3rd, ...** - Explanatory form card selection and ranking \r\n     cards fulfill requirement? - After the card selection, participants were asked whether the selected card combination fulfill their explainability requirement.\r\n\r\n\r\n2  [EUCA_EndUserXAI_demography.csv](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/EUCA_EndUserXAI_demography.csv)\r\n\r\n   It contains the participants demographics, including their age, gender, educational background, and their knowledge and attitudes toward AI.\r\n\r\n[EUCA dataset zip file for download](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/EUCA_Dataset.zip)\r\n\r\n\r\n## More Context for EUCA Dataset\r\n\r\n### [1] Critical tasks\r\n\r\nThere are four tasks. Task label and their corresponding task titles are:\r\nhouse - Selling your house \r\ncar - Buying an autonomous driving vehicle\r\nhealth - Personal health decision\r\nbird - Learning bird species\r\n\r\nPlease refer to [EUCA quantatative data analysis report](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/SupplementaryMaterialS2_UserStudy.pdf) for the storyboard of the tasks and explanation goals presented in the user study.\r\n\r\n### [2]  [Explanation goal](http://weina.me/end-user-xai/need.html)\r\n\r\nEnd-users may have different goals/purposes to check an explanation from AI. The EUCA dataset includes the following 11 explanation goals, with its [label] in the dataset, full name and description\r\n\r\n1. [trust] **[Calibrate trust](http://weina.me/end-user-xai/need.html#trust)**: trust is a key to\r\n   establish human-AI decision-making partnership. Since users can\r\n   easily distrust or overtrust AI, it is important to calibrate the\r\n   trust to reflect the capabilities of AI systems.\r\n2. [safe] **[Ensure safety](http://weina.me/end-user-xai/need.html#safe)**: users need to ensure\r\n   safety of the decision consequences.\r\n\r\n3. [bias] - **[Detect bias](http://weina.me/end-user-xai/need.html#bias)**: users need to ensure the\r\n   decision is impartial and unbiased.\r\n\r\n4. [unexpect] **[Resolve disagreement with AI](http://weina.me/end-user-xai/need.html#unexpected)**: the AI\r\n   prediction is *unexpected* and there are\r\n   disagreements between users and AI. \r\n\r\n 5. [expected] - **[Expected](http://weina.me/end-user-xai/need.html#expected)**: the AI's prediction is\r\n    *expected* and aligns with users'\r\n    expectations.\r\n\r\n6. [differentiate] **[Differentiate similar instances](http://weina.me/end-user-xai/need.html#differentiate)**: due to\r\n   the consequences of wrong decisions, users sometimes need to discern\r\n   similar instances or outcomes. For example, a doctor differentiates\r\n   whether the diagnosis is a benign or malignant tumor.\r\n\r\n7. [learning] **[Learn](http://weina.me/end-user-xai/need.html#learn)**: users need to gain knowledge,\r\n   improve their problem-solving skills, and discover new knowledge\r\n\r\n8. [control] **[Improve](http://weina.me/end-user-xai/need.html#improve)**: users seek causal factors to\r\n   control and improve the predicted outcome.\r\n\r\n9. [communicate] **[Communicate with stakeholders](http://weina.me/end-user-xai/need.html#communicate)**: many\r\n   critical decision-making processes involve multiple stakeholders,\r\n   and users need to discuss the decision with them.\r\n\r\n10. [report] **[Generate reports](http://weina.me/end-user-xai/need.html#report)**: users need to utilize\r\n    the explanations to perform particular tasks such as report\r\n    production. For example, a radiologist generates a medical report on\r\n    a patient's X-ray image.\r\n\r\n11. [multi] **[Trade-off multiple objectives](http://weina.me/end-user-xai/need.html#multi)**: AI may be\r\n    optimized on an incomplete objective while the users seek to fulfill\r\n    multiple objectives in real-world applications. For example, a\r\n    doctor needs to ensure a treatment plan is effective as well as has\r\n    acceptable patient adherence. Ethical and legal requirements may\r\n    also be included as objectives.\r\n\r\n### [3] [Explanatory form](http://weina.me/end-user-xai/explanatory_form.html)\r\n\r\nThe following 12 explanatory forms are end-user-friendly, i.e.: no technical knowledge is required for the end-user to interpret the explanation.\r\n\r\n\r\n* [Feature-Based Explanation](http://weina.me/end-user-xai/explanatory_form.html/#feature)\r\n  * Feature Attribution - fa\t\r\n    * Note: for tasks that has image as input data, the feature attribution is denoted by the following two cards:\r\n    * ir:  important regions (a.k.a. heat map or saliency map)\r\n    * irc: important regions with their feature contribution percentage\r\n  * Feature Shape - fs\r\n  * Feature Interaction - fi\r\n\r\n* [Example-Based Explanation](http://weina.me/end-user-xai/explanatory_form.html/#example)\r\n  * Similar Example - se\r\n  * Typical Example - te\r\n  * Counterfactual Example - ce\r\n    * Note: for contractual example, there were two visual variations used in the user study:\r\n    * cet:  counterfactual example with transition from one example to the counterfactual one\r\n    * ceh:  counterfactual example with the contrastive feature highlighted\r\n\r\n* [Rule-Based Explanation](http://weina.me/end-user-xai/explanatory_form.html/#rule)\r\n  * Rule - rt\r\n  * Decision Tree - dt\r\n  * Decision Flow - df\r\n\r\n* [Supplementary Information](http://weina.me/end-user-xai/explanatory_form.html/#suppl)\r\n  * Input\r\n  * Output\r\n  * Performance\r\n  * Dataset - prior  (output prediction with prior distribution of each class in the training set)\r\n\r\nNote: occasionally there is a wild card, which means the participant draw the card by themselves. It is indicated as 'wc'.\r\n\r\nFor visual examples of each explanatory form card, please refer to the [Explanatory_form_labels.pdf](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/EUCA_explanatory_form_labels.pdf) document.\r\n\r\n[Link to the details on users' requirements on different explanatory forms](http://weina.me/end-user-xai/explanatory_form.html)\r\n\r\n## Code and report for EUCA data quantatitve analysis\r\n\r\n* [EUCA data analysis code](https://github.com/weinajin/end-user-xai/tree/master/SupplementaryMaterialS4_EUCA_data_analysis_code)\r\n* [EUCA quantatative data analysis report](https://github.com/weinajin/end-user-xai/blob/master/SupplementaryMaterialS3_EUCA_Dataset/SupplementaryMaterialS2_UserStudy.pdf)\r\n\r\n## EUCA data citation\r\n\r\n```\r\n@article{jin2021euca,\r\n   title={EUCA: the End-User-Centered Explainable AI Framework},\r\n      author={Weina Jin and Jianyu Fan and Diane Gromala and Philippe Pasquier and Ghassan Hamarneh},\r\n      year={2021},\r\n      eprint={2102.02437},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.HC}\r\n}\r\n```","description_withheld":null,"homepage":"https://github.com/weinajin/euca/tree/master/EUCA_dataset_quantitative_and_qualitative_data","introduced_date":"2021-02-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/euca-a-practical-prototyping-framework","title":"EUCA: the End-User-Centered Explainable AI Framework","first_author":null,"url":null},"license":null,"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Explainable artificial intelligence","url":"/task/explainable-artificial-intelligence","datasets_with_task":"/datasets/task/explainable-artificial-intelligence"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["EUCA dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":0,"of":0,"counts":{"papers_with_a_benchmark_row":0,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":0,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"f946b324b15228c0238a9fb6dca59f93935c295106a15602e523184c5c1ec381","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}