{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QCRLOVGLHMSH2QL6AXZGSPUMRV","short_pith_number":"pith:QCRLOVGL","schema_version":"1.0","canonical_sha256":"80a2b754cb3b247d417e05f2693e8c8d4e3aa1f43a631861ad12162282242b07","source":{"kind":"arxiv","id":"2505.22450","version":1},"attestation_state":"computed","paper":{"title":"Position: All Current Generative Fidelity and Diversity Metrics are Flawed","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Mihaela van der Schaar, Ossi R\\\"ais\\\"a","submitted_at":"2025-05-28T15:10:33Z","abstract_excerpt":"Any method's development and practical application is limited by our ability to measure its reliability. The popularity of generative modeling emphasizes the importance of good synthetic data metrics. Unfortunately, previous works have found many failure cases in current metrics, for example lack of outlier robustness and unclear lower and upper bounds. We propose a list of desiderata for synthetic data metrics, and a suite of sanity checks: carefully chosen simple experiments that aim to detect specific and known generative modeling failure modes. Based on these desiderata and the results of "},"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":"2505.22450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T15:10:33Z","cross_cats_sorted":[],"title_canon_sha256":"6889a067c6d4335ef61e96637427aa1e620836aeabcb565e07811ec1b1229608","abstract_canon_sha256":"bb04f35e29c02aebc57828d8b7ca2328dc96a47dc32d1061a49268dec6c25a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:24.275609Z","signature_b64":"qJraP8cJOTVj3YGlCEnZc9qsc1YoIxPTngdji8HSzk2ebwLXZiuamG2zBq9QWcgP0J6qYRn8TbljC1hz0IcPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80a2b754cb3b247d417e05f2693e8c8d4e3aa1f43a631861ad12162282242b07","last_reissued_at":"2026-07-05T11:11:24.274962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:24.274962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: All Current Generative Fidelity and Diversity Metrics are Flawed","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Mihaela van der Schaar, Ossi R\\\"ais\\\"a","submitted_at":"2025-05-28T15:10:33Z","abstract_excerpt":"Any method's development and practical application is limited by our ability to measure its reliability. The popularity of generative modeling emphasizes the importance of good synthetic data metrics. Unfortunately, previous works have found many failure cases in current metrics, for example lack of outlier robustness and unclear lower and upper bounds. We propose a list of desiderata for synthetic data metrics, and a suite of sanity checks: carefully chosen simple experiments that aim to detect specific and known generative modeling failure modes. Based on these desiderata and the results of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22450","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/2505.22450/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":"2505.22450","created_at":"2026-07-05T11:11:24.275025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22450v1","created_at":"2026-07-05T11:11:24.275025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22450","created_at":"2026-07-05T11:11:24.275025+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCRLOVGLHMSH","created_at":"2026-07-05T11:11:24.275025+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCRLOVGLHMSH2QL6","created_at":"2026-07-05T11:11:24.275025+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCRLOVGL","created_at":"2026-07-05T11:11:24.275025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28914","citing_title":"Bayesian Posterior Sampling for Synthetic Shape Generation of Heart Valves","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV","json":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV.json","graph_json":"https://pith.science/api/pith-number/QCRLOVGLHMSH2QL6AXZGSPUMRV/graph.json","events_json":"https://pith.science/api/pith-number/QCRLOVGLHMSH2QL6AXZGSPUMRV/events.json","paper":"https://pith.science/paper/QCRLOVGL"},"agent_actions":{"view_html":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV","download_json":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV.json","view_paper":"https://pith.science/paper/QCRLOVGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22450&json=true","fetch_graph":"https://pith.science/api/pith-number/QCRLOVGLHMSH2QL6AXZGSPUMRV/graph.json","fetch_events":"https://pith.science/api/pith-number/QCRLOVGLHMSH2QL6AXZGSPUMRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV/action/storage_attestation","attest_author":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV/action/author_attestation","sign_citation":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV/action/citation_signature","submit_replication":"https://pith.science/pith/QCRLOVGLHMSH2QL6AXZGSPUMRV/action/replication_record"}},"created_at":"2026-07-05T11:11:24.275025+00:00","updated_at":"2026-07-05T11:11:24.275025+00:00"}