{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XOIEX2UJZAOUTZ5ESI4DXPUJNU","short_pith_number":"pith:XOIEX2UJ","schema_version":"1.0","canonical_sha256":"bb904bea89c81d49e7a492383bbe896d2109645dc001504e088a2fa1b38c4dc5","source":{"kind":"arxiv","id":"1903.02271","version":2},"attestation_state":"computed","paper":{"title":"High-Fidelity Image Generation With Fewer Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario Lucic, Marvin Ritter, Michael Tschannen, Olivier Bachem, Sylvain Gelly, Xiaohua Zhai","submitted_at":"2019-03-06T09:52:49Z","abstract_excerpt":"Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform the state of the art on both unsupervised ImageNet synthesis, as well as in the conditional sett"},"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":"1903.02271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-06T09:52:49Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2e20b7a6f110eb846d0baefc91e1102a2c4c9744c04fa9e66c7b9bfa46d60d8e","abstract_canon_sha256":"d5d4032b470e42a0d1548b375a18461096dea9f74810a6078c8289b8bc1ed2da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:18.353614Z","signature_b64":"rLENp9maj1zz3Oc9AAYRhYNiDTno2XQltyaKtK6bh0vUz4EnxwyGwke/MrEdQOR6EOUabnYkoXJUHm39gvfGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb904bea89c81d49e7a492383bbe896d2109645dc001504e088a2fa1b38c4dc5","last_reissued_at":"2026-05-17T23:46:18.352877Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:18.352877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Image Generation With Fewer Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario Lucic, Marvin Ritter, Michael Tschannen, Olivier Bachem, Sylvain Gelly, Xiaohua Zhai","submitted_at":"2019-03-06T09:52:49Z","abstract_excerpt":"Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform the state of the art on both unsupervised ImageNet synthesis, as well as in the conditional sett"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02271","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":""},"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":"1903.02271","created_at":"2026-05-17T23:46:18.352997+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02271v2","created_at":"2026-05-17T23:46:18.352997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02271","created_at":"2026-05-17T23:46:18.352997+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOIEX2UJZAOU","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOIEX2UJZAOUTZ5E","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOIEX2UJ","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU","json":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU.json","graph_json":"https://pith.science/api/pith-number/XOIEX2UJZAOUTZ5ESI4DXPUJNU/graph.json","events_json":"https://pith.science/api/pith-number/XOIEX2UJZAOUTZ5ESI4DXPUJNU/events.json","paper":"https://pith.science/paper/XOIEX2UJ"},"agent_actions":{"view_html":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU","download_json":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU.json","view_paper":"https://pith.science/paper/XOIEX2UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/XOIEX2UJZAOUTZ5ESI4DXPUJNU/graph.json","fetch_events":"https://pith.science/api/pith-number/XOIEX2UJZAOUTZ5ESI4DXPUJNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU/action/storage_attestation","attest_author":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU/action/author_attestation","sign_citation":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU/action/citation_signature","submit_replication":"https://pith.science/pith/XOIEX2UJZAOUTZ5ESI4DXPUJNU/action/replication_record"}},"created_at":"2026-05-17T23:46:18.352997+00:00","updated_at":"2026-05-17T23:46:18.352997+00:00"}