{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2NLZQLG57GEEISSDIPHYGLIMBM","short_pith_number":"pith:2NLZQLG5","schema_version":"1.0","canonical_sha256":"d357982cddf988444a4343cf832d0c0b3b5c9d2ad6ba807b2375a94e9f38a044","source":{"kind":"arxiv","id":"1904.06991","version":3},"attestation_state":"computed","paper":{"title":"Improved Precision and Recall Metric for Assessing Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Jaakko Lehtinen, Samuli Laine, Tero Karras, Timo Aila, Tuomas Kynk\\\"a\\\"anniemi","submitted_at":"2019-04-15T12:20:32Z","abstract_excerpt":"The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric representations of the manifolds of real and generated data. We demonstrate the effectiveness of our metric in StyleGAN and BigGAN by providing several illustrative examples where existing metrics yield uninformative or contradictory results. Furthermore, we analyze multiple des"},"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":"1904.06991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-15T12:20:32Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"0d9d3030a7b49f38f128242835187243928009889dbc7907e09ca7ad3c1c3332","abstract_canon_sha256":"46c5f2feddf62b4d746f462fb5adc188d4eeb5ec721a3fe216e0e6cc3747730f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:47.560999Z","signature_b64":"8RakeVu7KOZQlihBzzZEO4aJ+pAyjmFmFgdll17Dgbz5cKWaRUt/zhVazngMiPbFTfJD9jFTwrwpQOXr5PpAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d357982cddf988444a4343cf832d0c0b3b5c9d2ad6ba807b2375a94e9f38a044","last_reissued_at":"2026-07-05T00:15:47.560500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:47.560500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Precision and Recall Metric for Assessing Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Jaakko Lehtinen, Samuli Laine, Tero Karras, Timo Aila, Tuomas Kynk\\\"a\\\"anniemi","submitted_at":"2019-04-15T12:20:32Z","abstract_excerpt":"The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric representations of the manifolds of real and generated data. We demonstrate the effectiveness of our metric in StyleGAN and BigGAN by providing several illustrative examples where existing metrics yield uninformative or contradictory results. Furthermore, we analyze multiple des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06991","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/1904.06991/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":"1904.06991","created_at":"2026-07-05T00:15:47.560559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06991v3","created_at":"2026-07-05T00:15:47.560559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06991","created_at":"2026-07-05T00:15:47.560559+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NLZQLG57GEE","created_at":"2026-07-05T00:15:47.560559+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NLZQLG57GEEISSD","created_at":"2026-07-05T00:15:47.560559+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NLZQLG5","created_at":"2026-07-05T00:15:47.560559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13364","citing_title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11096","citing_title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00377","citing_title":"Score-Control for Hallucination Reduction in Diffusion Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01675","citing_title":"GRASP: Guided Residual Adapters with Sample-wise Partitioning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM","json":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM.json","graph_json":"https://pith.science/api/pith-number/2NLZQLG57GEEISSDIPHYGLIMBM/graph.json","events_json":"https://pith.science/api/pith-number/2NLZQLG57GEEISSDIPHYGLIMBM/events.json","paper":"https://pith.science/paper/2NLZQLG5"},"agent_actions":{"view_html":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM","download_json":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM.json","view_paper":"https://pith.science/paper/2NLZQLG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06991&json=true","fetch_graph":"https://pith.science/api/pith-number/2NLZQLG57GEEISSDIPHYGLIMBM/graph.json","fetch_events":"https://pith.science/api/pith-number/2NLZQLG57GEEISSDIPHYGLIMBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM/action/storage_attestation","attest_author":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM/action/author_attestation","sign_citation":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM/action/citation_signature","submit_replication":"https://pith.science/pith/2NLZQLG57GEEISSDIPHYGLIMBM/action/replication_record"}},"created_at":"2026-07-05T00:15:47.560559+00:00","updated_at":"2026-07-05T00:15:47.560559+00:00"}