{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HFNACMIB4XIXGXRMC6SHSLH2F2","short_pith_number":"pith:HFNACMIB","schema_version":"1.0","canonical_sha256":"395a013101e5d1735e2c17a4792cfa2e990a693f8da0252faa493befca72e25b","source":{"kind":"arxiv","id":"2501.00664","version":3},"attestation_state":"computed","paper":{"title":"Grade Inflation in Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alexandra Morgan, Miao Li, Phuc Nguyen, Ramy Arnaout, Rima Arnaout","submitted_at":"2024-12-31T22:34:54Z","abstract_excerpt":"Generative models hold great potential, but only if one can trust the evaluation of the data they generate. We show that many commonly used quality scores for comparing two-dimensional distributions of synthetic vs. ground-truth data give better results than they should, a phenomenon we call the \"grade inflation problem.\" We show that the correlation score, Jaccard score, earth-mover's score, and Kullback-Leibler (relative-entropy) score all suffer grade inflation. We propose that any score that values all datapoints equally, as these do, will also exhibit grade inflation; we refer to such sco"},"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":"2501.00664","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T22:34:54Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7a07486dd2005aa8b11865075594d2573264fb3e1589dbf05945263c73817633","abstract_canon_sha256":"1f5509363d0fae25a6aea04578ad6b879eff81e8c86f552eee87c20cd6120179"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:21.482115Z","signature_b64":"u65euzVY1RyVhAtHHqvCGKp6Fq8VJKP930yV2FcWvlc1bH4YHGrQQ7P7zJVdJGWezrBTrELdODnZ/i0BeCqRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395a013101e5d1735e2c17a4792cfa2e990a693f8da0252faa493befca72e25b","last_reissued_at":"2026-07-05T10:04:21.481648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:21.481648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grade Inflation in Generative Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alexandra Morgan, Miao Li, Phuc Nguyen, Ramy Arnaout, Rima Arnaout","submitted_at":"2024-12-31T22:34:54Z","abstract_excerpt":"Generative models hold great potential, but only if one can trust the evaluation of the data they generate. We show that many commonly used quality scores for comparing two-dimensional distributions of synthetic vs. ground-truth data give better results than they should, a phenomenon we call the \"grade inflation problem.\" We show that the correlation score, Jaccard score, earth-mover's score, and Kullback-Leibler (relative-entropy) score all suffer grade inflation. We propose that any score that values all datapoints equally, as these do, will also exhibit grade inflation; we refer to such sco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00664","kind":"arxiv","version":3},"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/2501.00664/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":"2501.00664","created_at":"2026-07-05T10:04:21.481705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00664v3","created_at":"2026-07-05T10:04:21.481705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00664","created_at":"2026-07-05T10:04:21.481705+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFNACMIB4XIX","created_at":"2026-07-05T10:04:21.481705+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFNACMIB4XIXGXRM","created_at":"2026-07-05T10:04:21.481705+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFNACMIB","created_at":"2026-07-05T10:04:21.481705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2","json":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2.json","graph_json":"https://pith.science/api/pith-number/HFNACMIB4XIXGXRMC6SHSLH2F2/graph.json","events_json":"https://pith.science/api/pith-number/HFNACMIB4XIXGXRMC6SHSLH2F2/events.json","paper":"https://pith.science/paper/HFNACMIB"},"agent_actions":{"view_html":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2","download_json":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2.json","view_paper":"https://pith.science/paper/HFNACMIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00664&json=true","fetch_graph":"https://pith.science/api/pith-number/HFNACMIB4XIXGXRMC6SHSLH2F2/graph.json","fetch_events":"https://pith.science/api/pith-number/HFNACMIB4XIXGXRMC6SHSLH2F2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2/action/storage_attestation","attest_author":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2/action/author_attestation","sign_citation":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2/action/citation_signature","submit_replication":"https://pith.science/pith/HFNACMIB4XIXGXRMC6SHSLH2F2/action/replication_record"}},"created_at":"2026-07-05T10:04:21.481705+00:00","updated_at":"2026-07-05T10:04:21.481705+00:00"}