{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4HHZO3BU5DTX7JLPID7GTFMEJ","short_pith_number":"pith:T4HHZO3B","schema_version":"1.0","canonical_sha256":"9f0e7cbb61a7473bfd2b7a07f34cac226c80a675fda469825b32c1ef8d02ddef","source":{"kind":"arxiv","id":"2408.11135","version":1},"attestation_state":"computed","paper":{"title":"MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiancheng Lv, Jian Wang, Xin Lan, Yuxin Tian","submitted_at":"2024-08-20T18:37:37Z","abstract_excerpt":"Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discriminator overfitting. To tackle this issue, we investigate the challenge of training GANs with limited data, and propose a novel regularization method based on the idea of renormalization group (RG) in physics.We observe that in the limited data setting, the gradient pattern that the generator obtains from the discriminator becomes more aggregated over time. In RG context, this aggregated pattern exhibits a high discrepan"},"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":"2408.11135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-20T18:37:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b11cf4de92905ed6c31b25a0dca49d8cd7c3510973555f32ba92f41f90da777f","abstract_canon_sha256":"22be3bd9137527b1df77157bac709bae87b2140b4eefe181ea292e4fa74a9fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:25.374379Z","signature_b64":"pQpQjzHMwbnhCKyoQxcr+8VlKeR3uaV9zS8dBxWLGiDiJxKFSqwZQUQkC0NkCXuWg48AsHbDXe5X6/FGG8nCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0e7cbb61a7473bfd2b7a07f34cac226c80a675fda469825b32c1ef8d02ddef","last_reissued_at":"2026-07-05T08:57:25.373873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:25.373873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiancheng Lv, Jian Wang, Xin Lan, Yuxin Tian","submitted_at":"2024-08-20T18:37:37Z","abstract_excerpt":"Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discriminator overfitting. To tackle this issue, we investigate the challenge of training GANs with limited data, and propose a novel regularization method based on the idea of renormalization group (RG) in physics.We observe that in the limited data setting, the gradient pattern that the generator obtains from the discriminator becomes more aggregated over time. In RG context, this aggregated pattern exhibits a high discrepan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11135","kind":"arxiv","version":1},"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/2408.11135/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":"2408.11135","created_at":"2026-07-05T08:57:25.373930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11135v1","created_at":"2026-07-05T08:57:25.373930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11135","created_at":"2026-07-05T08:57:25.373930+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4HHZO3BU5DT","created_at":"2026-07-05T08:57:25.373930+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4HHZO3BU5DTX7JL","created_at":"2026-07-05T08:57:25.373930+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4HHZO3B","created_at":"2026-07-05T08:57:25.373930+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/T4HHZO3BU5DTX7JLPID7GTFMEJ","json":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ.json","graph_json":"https://pith.science/api/pith-number/T4HHZO3BU5DTX7JLPID7GTFMEJ/graph.json","events_json":"https://pith.science/api/pith-number/T4HHZO3BU5DTX7JLPID7GTFMEJ/events.json","paper":"https://pith.science/paper/T4HHZO3B"},"agent_actions":{"view_html":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ","download_json":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ.json","view_paper":"https://pith.science/paper/T4HHZO3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11135&json=true","fetch_graph":"https://pith.science/api/pith-number/T4HHZO3BU5DTX7JLPID7GTFMEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T4HHZO3BU5DTX7JLPID7GTFMEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ/action/storage_attestation","attest_author":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ/action/author_attestation","sign_citation":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ/action/citation_signature","submit_replication":"https://pith.science/pith/T4HHZO3BU5DTX7JLPID7GTFMEJ/action/replication_record"}},"created_at":"2026-07-05T08:57:25.373930+00:00","updated_at":"2026-07-05T08:57:25.373930+00:00"}