{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TOC24X77EXHNW5VZ23FUMMX4ND","short_pith_number":"pith:TOC24X77","schema_version":"1.0","canonical_sha256":"9b85ae5fff25cedb76b9d6cb4632fc68e35477fdc489b78aa922e6dacb84c386","source":{"kind":"arxiv","id":"1705.09367","version":2},"attestation_state":"computed","paper":{"title":"Stabilizing Training of Generative Adversarial Networks through Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Kevin Roth, Sebastian Nowozin, Thomas Hofmann","submitted_at":"2017-05-25T21:17:50Z","abstract_excerpt":"Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch or non-overlapping support between the model distribution and the data distribution, causing their density ratio and the associated f-divergence to be undefined. We overcome this fundamental limitation and propose a new regularization approach with low computational cost that yields a stable GAN tra"},"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":"1705.09367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-25T21:17:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15f7d5bf04e864a2c5deb5521cc137893e1c0a234ec8e099d3260e66ed937150","abstract_canon_sha256":"8e51de41494f5d1ee704c017f4b65b8641087a81d553682dbbb03b788753a238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:12.674343Z","signature_b64":"dRhK8d0AoNfYjtX0rizW68v5LR8gLeFguTMWjRpROgv++yFq2uW/WbJea/Nkwo0aawggyOZCIeI1WH+jxoP+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b85ae5fff25cedb76b9d6cb4632fc68e35477fdc489b78aa922e6dacb84c386","last_reissued_at":"2026-05-18T00:31:12.673597Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:12.673597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilizing Training of Generative Adversarial Networks through Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Kevin Roth, Sebastian Nowozin, Thomas Hofmann","submitted_at":"2017-05-25T21:17:50Z","abstract_excerpt":"Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch or non-overlapping support between the model distribution and the data distribution, causing their density ratio and the associated f-divergence to be undefined. We overcome this fundamental limitation and propose a new regularization approach with low computational cost that yields a stable GAN tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09367","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":"1705.09367","created_at":"2026-05-18T00:31:12.673718+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09367v2","created_at":"2026-05-18T00:31:12.673718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09367","created_at":"2026-05-18T00:31:12.673718+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOC24X77EXHN","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOC24X77EXHNW5VZ","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOC24X77","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21573","citing_title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND","json":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND.json","graph_json":"https://pith.science/api/pith-number/TOC24X77EXHNW5VZ23FUMMX4ND/graph.json","events_json":"https://pith.science/api/pith-number/TOC24X77EXHNW5VZ23FUMMX4ND/events.json","paper":"https://pith.science/paper/TOC24X77"},"agent_actions":{"view_html":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND","download_json":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND.json","view_paper":"https://pith.science/paper/TOC24X77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09367&json=true","fetch_graph":"https://pith.science/api/pith-number/TOC24X77EXHNW5VZ23FUMMX4ND/graph.json","fetch_events":"https://pith.science/api/pith-number/TOC24X77EXHNW5VZ23FUMMX4ND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND/action/storage_attestation","attest_author":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND/action/author_attestation","sign_citation":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND/action/citation_signature","submit_replication":"https://pith.science/pith/TOC24X77EXHNW5VZ23FUMMX4ND/action/replication_record"}},"created_at":"2026-05-18T00:31:12.673718+00:00","updated_at":"2026-05-18T00:31:12.673718+00:00"}