{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/how-faithful-is-your-synthetic-data-sample","title":"How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models","arxiv_id":"2102.08921","date":"2021-02-17","proceeding":null,"authors":["Ahmed M. Alaa","Boris van Breugel","Evgeny Saveliev","Mihaela van der Schaar"],"abstract":"Devising domain- and model-agnostic evaluation metrics for generative models is an important and as yet unresolved problem. Most existing metrics, which were tailored solely to the image synthesis setup, exhibit a limited capacity for diagnosing the different modes of failure of generative models across broader application domains. In this paper, we introduce a 3-dimensional evaluation metric, ($\\alpha$-Precision, $\\beta$-Recall, Authenticity), that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity. We introduce generalization as an additional, independent dimension (to the fidelity-diversity trade-off) that quantifies the extent to which a model copies training data -- a crucial performance indicator when modeling sensitive data with requirements on privacy. The three metric components correspond to (interpretable) probabilistic quantities, and are estimated via sample-level binary classification. The sample-level nature of our metric inspires a novel use case which we call model auditing, wherein we judge the quality of individual samples generated by a (black-box) model, discarding low-quality samples and hence improving the overall model performance in a post-hoc manner.","url_abs":"https://arxiv.org/abs/2102.08921v2","url_pdf":"https://arxiv.org/pdf/2102.08921v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"how-faithful-is-your-synthetic-data-sample","repo_url":"https://github.com/vanderschaarlab/evaluating-generative-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"how-faithful-is-your-synthetic-data-sample","repo_url":"https://github.com/amazon-science/tabsyn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-faithful-is-your-synthetic-data-sample","repo_url":"https://github.com/fangzy96/tabcutmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-faithful-is-your-synthetic-data-sample","repo_url":"https://github.com/marcojira/fls","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.08921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08921"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marcojira/fls","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amazon-science/tabsyn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fangzy96/tabcutmix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vanderschaarlab/evaluating-generative-models","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"9c5d287ad510cbe1","entry":"compute_alpha_precision","repo":"vanderschaarlab/evaluating-generative-models","repo_kind":"official","path":"metrics/evaluation.py","file_url":"https://github.com/vanderschaarlab/evaluating-generative-models/blob/HEAD/metrics/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c5d287ad510cbe1"}},{"code_sha256_prefix":"49f8fe0655f00ee5","entry":"geglu","repo":"fangzy96/tabcutmix","repo_kind":"listed","path":"tabsyn/model.py","file_url":"https://github.com/fangzy96/tabcutmix/blob/HEAD/tabsyn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49f8fe0655f00ee5"}},{"code_sha256_prefix":"58bd3831c7fb6729","entry":"reglu","repo":"fangzy96/tabcutmix","repo_kind":"listed","path":"tabsyn/model.py","file_url":"https://github.com/fangzy96/tabcutmix/blob/HEAD/tabsyn/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58bd3831c7fb6729"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}