{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:V2KQA76QYTPYQ3KAA3XFDKUEY5","short_pith_number":"pith:V2KQA76Q","schema_version":"1.0","canonical_sha256":"ae95007fd0c4df886d4006ee51aa84c7429f256f2965cafe3b5e00b827495f32","source":{"kind":"arxiv","id":"2006.06676","version":2},"attestation_state":"computed","paper":{"title":"Training Generative Adversarial Networks with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaakko Lehtinen, Janne Hellsten, Miika Aittala, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2020-06-11T17:06:34Z","abstract_excerpt":"Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 res"},"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":"2006.06676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-11T17:06:34Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"3cb5a24195a531178378ffbcf97962eba6e6afc4db9a843069abbe9131d09e6b","abstract_canon_sha256":"7a440bf273c58a2158360dc7b8a4358ee0f5cb8a225f6e8810ecd49dce4377af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:08.525699Z","signature_b64":"7RiawKxcO2vCJLpMRY/z8u6w+aLaECXoQyJU95z5S0WKtr4IvkzeYGIKWFf7bpv71kuuVVI0QWNzR9TMvCXxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae95007fd0c4df886d4006ee51aa84c7429f256f2965cafe3b5e00b827495f32","last_reissued_at":"2026-07-05T01:41:08.525247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:08.525247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Generative Adversarial Networks with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jaakko Lehtinen, Janne Hellsten, Miika Aittala, Samuli Laine, Tero Karras, Timo Aila","submitted_at":"2020-06-11T17:06:34Z","abstract_excerpt":"Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06676","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/2006.06676/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":"2006.06676","created_at":"2026-07-05T01:41:08.525304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06676v2","created_at":"2026-07-05T01:41:08.525304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06676","created_at":"2026-07-05T01:41:08.525304+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2KQA76QYTPY","created_at":"2026-07-05T01:41:08.525304+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2KQA76QYTPYQ3KA","created_at":"2026-07-05T01:41:08.525304+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2KQA76Q","created_at":"2026-07-05T01:41:08.525304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05138","citing_title":"Generating Financial Time Series by Matching Random Convolutional Features","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05691","citing_title":"SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2101.02388","citing_title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02438","citing_title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2108.01073","citing_title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2006.11239","citing_title":"Denoising Diffusion Probabilistic Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06678","citing_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5","json":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5.json","graph_json":"https://pith.science/api/pith-number/V2KQA76QYTPYQ3KAA3XFDKUEY5/graph.json","events_json":"https://pith.science/api/pith-number/V2KQA76QYTPYQ3KAA3XFDKUEY5/events.json","paper":"https://pith.science/paper/V2KQA76Q"},"agent_actions":{"view_html":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5","download_json":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5.json","view_paper":"https://pith.science/paper/V2KQA76Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06676&json=true","fetch_graph":"https://pith.science/api/pith-number/V2KQA76QYTPYQ3KAA3XFDKUEY5/graph.json","fetch_events":"https://pith.science/api/pith-number/V2KQA76QYTPYQ3KAA3XFDKUEY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5/action/storage_attestation","attest_author":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5/action/author_attestation","sign_citation":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5/action/citation_signature","submit_replication":"https://pith.science/pith/V2KQA76QYTPYQ3KAA3XFDKUEY5/action/replication_record"}},"created_at":"2026-07-05T01:41:08.525304+00:00","updated_at":"2026-07-05T01:41:08.525304+00:00"}