{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IEAAS65K3YPEEELZUIJ4BVJYJC","short_pith_number":"pith:IEAAS65K","schema_version":"1.0","canonical_sha256":"4100097baade1e421179a213c0d53848b33265d86f9ae1524351832210455c2d","source":{"kind":"arxiv","id":"1705.07215","version":5},"attestation_state":"computed","paper":{"title":"On Convergence and Stability of GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GT","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Jacob Abernethy, James Hays, Naveen Kodali, Zsolt Kira","submitted_at":"2017-05-19T22:41:56Z","abstract_excerpt":"We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions. We analyze the convergence of GAN training from this new point of view to understand why mode collapse happens. We hypothesize the existence of undesirable local equilibria in this non-convex game to be responsible for mode collapse. We observe that these local equilibria often exhibit sharp gradients of the discriminator function around some real data points. We demonstrate that these degenera"},"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":"1705.07215","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-19T22:41:56Z","cross_cats_sorted":["cs.CV","cs.GT","cs.LG","cs.NE"],"title_canon_sha256":"b2dbc12385b297978a49c69e3f9d632d2af960bf625095dc0b8137736b403572","abstract_canon_sha256":"1d3b6e01d9a3a7c6dfaa5d1d7b7be67aa16d5ad15c01694b8f9b5d6b1cdd71b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:25.335143Z","signature_b64":"dA10j8wJmmm4iLVdKaMqn166yuSt1G2itByMwaGawHfUA9b2/GebFrJ199zjbg4WDE2bC9Vp+oGoT1qU5lhlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4100097baade1e421179a213c0d53848b33265d86f9ae1524351832210455c2d","last_reissued_at":"2026-05-18T00:28:25.334286Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:25.334286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Convergence and Stability of GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GT","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Jacob Abernethy, James Hays, Naveen Kodali, Zsolt Kira","submitted_at":"2017-05-19T22:41:56Z","abstract_excerpt":"We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions. We analyze the convergence of GAN training from this new point of view to understand why mode collapse happens. We hypothesize the existence of undesirable local equilibria in this non-convex game to be responsible for mode collapse. We observe that these local equilibria often exhibit sharp gradients of the discriminator function around some real data points. We demonstrate that these degenera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07215","kind":"arxiv","version":5},"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":"1705.07215","created_at":"2026-05-18T00:28:25.334467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07215v5","created_at":"2026-05-18T00:28:25.334467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07215","created_at":"2026-05-18T00:28:25.334467+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEAAS65K3YPE","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEAAS65K3YPEEELZ","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEAAS65K","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.09691","citing_title":"Adversarial Computation of Optimal Transport Maps","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2410.08329","citing_title":"Survey of Deep Learning and Physics-Based Approaches in Computational Wave Imaging","ref_index":139,"is_internal_anchor":true},{"citing_arxiv_id":"2505.14202","citing_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2507.02314","citing_title":"MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1809.11096","citing_title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"1710.10196","citing_title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","ref_index":27,"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":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21097","citing_title":"Learning to Emulate Chaos: Adversarial Optimal Transport Regularization","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC","json":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC.json","graph_json":"https://pith.science/api/pith-number/IEAAS65K3YPEEELZUIJ4BVJYJC/graph.json","events_json":"https://pith.science/api/pith-number/IEAAS65K3YPEEELZUIJ4BVJYJC/events.json","paper":"https://pith.science/paper/IEAAS65K"},"agent_actions":{"view_html":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC","download_json":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC.json","view_paper":"https://pith.science/paper/IEAAS65K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07215&json=true","fetch_graph":"https://pith.science/api/pith-number/IEAAS65K3YPEEELZUIJ4BVJYJC/graph.json","fetch_events":"https://pith.science/api/pith-number/IEAAS65K3YPEEELZUIJ4BVJYJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC/action/storage_attestation","attest_author":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC/action/author_attestation","sign_citation":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC/action/citation_signature","submit_replication":"https://pith.science/pith/IEAAS65K3YPEEELZUIJ4BVJYJC/action/replication_record"}},"created_at":"2026-05-18T00:28:25.334467+00:00","updated_at":"2026-05-18T00:28:25.334467+00:00"}