{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LCZ2SVX7R6JNRKVECJFQ42DYLW","short_pith_number":"pith:LCZ2SVX7","schema_version":"1.0","canonical_sha256":"58b3a956ff8f92d8aaa4124b0e68785d89a31e93c9776aae2a4aff530dde80d8","source":{"kind":"arxiv","id":"2002.09797","version":2},"attestation_state":"computed","paper":{"title":"Reliable Fidelity and Diversity Metrics for Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaejun Yoo, Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi","submitted_at":"2020-02-23T00:50:01Z","abstract_excerpt":"Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated images has been the Fr\\'echet Inception Distance (FID) score. Because it does not differentiate the fidelity and diversity aspects of the generated images, recent papers have introduced variants of precision and recall metrics to diagnose those properties separately. In this paper, we show that even the latest version of the precision and recall metrics are not reliable yet. For example, they fail to detect the match b"},"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":"2002.09797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-23T00:50:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c09c93674b51b08a78d3654c62ffdbc3d65f72f1e56b220e71577ac1fe107046","abstract_canon_sha256":"4736d701ccf3b956cc56e737f2b2b93a71c68bdb797f5e5411a67abcf68d1d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:58.350901Z","signature_b64":"0P8efRME+qm+wgSw3giWHj2PjY1bL+DRtgjoxbcSJxIjwPFWWO+r1hVz1rXNmfMdmrZQy5wdTuYnGmgkIsB/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b3a956ff8f92d8aaa4124b0e68785d89a31e93c9776aae2a4aff530dde80d8","last_reissued_at":"2026-07-05T01:13:58.350453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:58.350453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Fidelity and Diversity Metrics for Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaejun Yoo, Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi","submitted_at":"2020-02-23T00:50:01Z","abstract_excerpt":"Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated images has been the Fr\\'echet Inception Distance (FID) score. Because it does not differentiate the fidelity and diversity aspects of the generated images, recent papers have introduced variants of precision and recall metrics to diagnose those properties separately. In this paper, we show that even the latest version of the precision and recall metrics are not reliable yet. For example, they fail to detect the match b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09797","kind":"arxiv","version":2},"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/2002.09797/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":"2002.09797","created_at":"2026-07-05T01:13:58.350509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09797v2","created_at":"2026-07-05T01:13:58.350509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09797","created_at":"2026-07-05T01:13:58.350509+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCZ2SVX7R6JN","created_at":"2026-07-05T01:13:58.350509+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCZ2SVX7R6JNRKVE","created_at":"2026-07-05T01:13:58.350509+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCZ2SVX7","created_at":"2026-07-05T01:13:58.350509+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/LCZ2SVX7R6JNRKVECJFQ42DYLW","json":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW.json","graph_json":"https://pith.science/api/pith-number/LCZ2SVX7R6JNRKVECJFQ42DYLW/graph.json","events_json":"https://pith.science/api/pith-number/LCZ2SVX7R6JNRKVECJFQ42DYLW/events.json","paper":"https://pith.science/paper/LCZ2SVX7"},"agent_actions":{"view_html":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW","download_json":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW.json","view_paper":"https://pith.science/paper/LCZ2SVX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09797&json=true","fetch_graph":"https://pith.science/api/pith-number/LCZ2SVX7R6JNRKVECJFQ42DYLW/graph.json","fetch_events":"https://pith.science/api/pith-number/LCZ2SVX7R6JNRKVECJFQ42DYLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW/action/storage_attestation","attest_author":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW/action/author_attestation","sign_citation":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW/action/citation_signature","submit_replication":"https://pith.science/pith/LCZ2SVX7R6JNRKVECJFQ42DYLW/action/replication_record"}},"created_at":"2026-07-05T01:13:58.350509+00:00","updated_at":"2026-07-05T01:13:58.350509+00:00"}