{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:73GDZ3ML2QPZD2KNK3QWKOC5AQ","short_pith_number":"pith:73GDZ3ML","schema_version":"1.0","canonical_sha256":"fecc3ced8bd41f91e94d56e165385d0418a6eff15a08c57bb68debdb4bc7fcfb","source":{"kind":"arxiv","id":"2405.15337","version":1},"attestation_state":"computed","paper":{"title":"Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chi-Hua Wang, Guang Cheng, Lan Tao, Namjoon Suh, Shirong Xu","submitted_at":"2024-05-24T08:18:09Z","abstract_excerpt":"With the proliferation of generative AI and the increasing volume of generative data (also called as synthetic data), assessing the fidelity of generative data has become a critical concern. In this paper, we propose a discriminative approach to estimate the total variation (TV) distance between two distributions as an effective measure of generative data fidelity. Our method quantitatively characterizes the relation between the Bayes risk in classifying two distributions and their TV distance. Therefore, the estimation of total variation distance reduces to that of the Bayes risk. In particul"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.15337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T08:18:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fc630074fcfa83e2e692158e01876ece6e8b58e707c5c5b9b62e651b3b3525a6","abstract_canon_sha256":"0641370f0c83d3f405db54967194f208b142cb38a1f1b872a36842bc5f3623c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:47.984288Z","signature_b64":"oTNjyGXwv8kfqy3fq5qj+3r/JT6wqPe/NbBJF672ipcakjEgxZuvPS29DlCrc/kDiEJuMInoaduzJriSwzeoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecc3ced8bd41f91e94d56e165385d0418a6eff15a08c57bb68debdb4bc7fcfb","last_reissued_at":"2026-07-05T08:22:47.983799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:47.983799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chi-Hua Wang, Guang Cheng, Lan Tao, Namjoon Suh, Shirong Xu","submitted_at":"2024-05-24T08:18:09Z","abstract_excerpt":"With the proliferation of generative AI and the increasing volume of generative data (also called as synthetic data), assessing the fidelity of generative data has become a critical concern. In this paper, we propose a discriminative approach to estimate the total variation (TV) distance between two distributions as an effective measure of generative data fidelity. Our method quantitatively characterizes the relation between the Bayes risk in classifying two distributions and their TV distance. Therefore, the estimation of total variation distance reduces to that of the Bayes risk. In particul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15337","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.15337/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.15337","created_at":"2026-07-05T08:22:47.983860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15337v1","created_at":"2026-07-05T08:22:47.983860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15337","created_at":"2026-07-05T08:22:47.983860+00:00"},{"alias_kind":"pith_short_12","alias_value":"73GDZ3ML2QPZ","created_at":"2026-07-05T08:22:47.983860+00:00"},{"alias_kind":"pith_short_16","alias_value":"73GDZ3ML2QPZD2KN","created_at":"2026-07-05T08:22:47.983860+00:00"},{"alias_kind":"pith_short_8","alias_value":"73GDZ3ML","created_at":"2026-07-05T08:22:47.983860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02072","citing_title":"Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ","json":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ.json","graph_json":"https://pith.science/api/pith-number/73GDZ3ML2QPZD2KNK3QWKOC5AQ/graph.json","events_json":"https://pith.science/api/pith-number/73GDZ3ML2QPZD2KNK3QWKOC5AQ/events.json","paper":"https://pith.science/paper/73GDZ3ML"},"agent_actions":{"view_html":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ","download_json":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ.json","view_paper":"https://pith.science/paper/73GDZ3ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15337&json=true","fetch_graph":"https://pith.science/api/pith-number/73GDZ3ML2QPZD2KNK3QWKOC5AQ/graph.json","fetch_events":"https://pith.science/api/pith-number/73GDZ3ML2QPZD2KNK3QWKOC5AQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ/action/storage_attestation","attest_author":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ/action/author_attestation","sign_citation":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ/action/citation_signature","submit_replication":"https://pith.science/pith/73GDZ3ML2QPZD2KNK3QWKOC5AQ/action/replication_record"}},"created_at":"2026-07-05T08:22:47.983860+00:00","updated_at":"2026-07-05T08:22:47.983860+00:00"}