{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PLGPCQBJEP3X7VWILAI63DC7XU","short_pith_number":"pith:PLGPCQBJ","schema_version":"1.0","canonical_sha256":"7accf1402923f77fd6c85811ed8c5fbd398f2916d09bb51274db4021cb418af9","source":{"kind":"arxiv","id":"2009.04433","version":2},"attestation_state":"computed","paper":{"title":"not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"eess.IV","authors_text":"Akash Srivastava, Cole Hurwitz, David D. Cox, Prasanna Sattigeri, Seungwook Han","submitted_at":"2020-09-09T17:29:40Z","abstract_excerpt":"State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train, putting them out of reach for the larger research community. On the other hand, GAN-based image super-resolution models, such as ESRGAN, can not only upscale images to high dimensions, but also are efficient to train. In this paper, we present not-so-big-GAN (nsb-GAN), a simple yet cost-effective two-step training framework for deep generative models (DGMs) of high-dimensional natural images. First, we generate imag"},"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":"2009.04433","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-09-09T17:29:40Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"f1749e0d3d26cb3c3205bcb19b0a09d102a654b5f2ee396c0bd8ed14edb202f4","abstract_canon_sha256":"0c6e2e2cfefce633bb75baba682f6657f5bce319583829a9bc367cfdb29b0407"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:44.974065Z","signature_b64":"lo9hLnE0BFT8NfGRktbwmDMX9yORcZy4ivxkE5v3Ry4h/42OlpZLzEz0AJRjs5ARBZhzyez4pKZT5VTzCZxxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7accf1402923f77fd6c85811ed8c5fbd398f2916d09bb51274db4021cb418af9","last_reissued_at":"2026-07-05T01:45:44.973599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:44.973599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"eess.IV","authors_text":"Akash Srivastava, Cole Hurwitz, David D. Cox, Prasanna Sattigeri, Seungwook Han","submitted_at":"2020-09-09T17:29:40Z","abstract_excerpt":"State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train, putting them out of reach for the larger research community. On the other hand, GAN-based image super-resolution models, such as ESRGAN, can not only upscale images to high dimensions, but also are efficient to train. In this paper, we present not-so-big-GAN (nsb-GAN), a simple yet cost-effective two-step training framework for deep generative models (DGMs) of high-dimensional natural images. First, we generate imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04433","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/2009.04433/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":"2009.04433","created_at":"2026-07-05T01:45:44.973656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.04433v2","created_at":"2026-07-05T01:45:44.973656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04433","created_at":"2026-07-05T01:45:44.973656+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLGPCQBJEP3X","created_at":"2026-07-05T01:45:44.973656+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLGPCQBJEP3X7VWI","created_at":"2026-07-05T01:45:44.973656+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLGPCQBJ","created_at":"2026-07-05T01:45:44.973656+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/PLGPCQBJEP3X7VWILAI63DC7XU","json":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU.json","graph_json":"https://pith.science/api/pith-number/PLGPCQBJEP3X7VWILAI63DC7XU/graph.json","events_json":"https://pith.science/api/pith-number/PLGPCQBJEP3X7VWILAI63DC7XU/events.json","paper":"https://pith.science/paper/PLGPCQBJ"},"agent_actions":{"view_html":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU","download_json":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU.json","view_paper":"https://pith.science/paper/PLGPCQBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.04433&json=true","fetch_graph":"https://pith.science/api/pith-number/PLGPCQBJEP3X7VWILAI63DC7XU/graph.json","fetch_events":"https://pith.science/api/pith-number/PLGPCQBJEP3X7VWILAI63DC7XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU/action/storage_attestation","attest_author":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU/action/author_attestation","sign_citation":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU/action/citation_signature","submit_replication":"https://pith.science/pith/PLGPCQBJEP3X7VWILAI63DC7XU/action/replication_record"}},"created_at":"2026-07-05T01:45:44.973656+00:00","updated_at":"2026-07-05T01:45:44.973656+00:00"}