{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7V34MZVXN5PTH7RXDT2KAEF5GU","short_pith_number":"pith:7V34MZVX","schema_version":"1.0","canonical_sha256":"fd77c666b76f5f33fe371cf4a010bd350bbb161e810c7940fba7ff40bf1bfac4","source":{"kind":"arxiv","id":"1612.02136","version":5},"attestation_state":"computed","paper":{"title":"Mode Regularized Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Athul Paul Jacob, Tong Che, Wenjie Li, Yanran Li, Yoshua Bengio","submitted_at":"2016-12-07T07:45:38Z","abstract_excerpt":"Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN mo"},"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":"1612.02136","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-07T07:45:38Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"92a8592f428a7f0c07524180830a9cb3c06018b104bc856c91e094b297cb81aa","abstract_canon_sha256":"7f4f8c14c2c277ea77f86de09c80bec99e9349d08c5eac351538d9ca792681df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:41.881375Z","signature_b64":"dXTP5KqYjvNVxInkIMC5wUPPfVIi4yk1Ji1oRTgRP/zp2PC+JpxzW37FdXlQbNwNYi38PKrN+62zN2aHR9avDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd77c666b76f5f33fe371cf4a010bd350bbb161e810c7940fba7ff40bf1bfac4","last_reissued_at":"2026-05-18T00:49:41.880962Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:41.880962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mode Regularized Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Athul Paul Jacob, Tong Che, Wenjie Li, Yanran Li, Yoshua Bengio","submitted_at":"2016-12-07T07:45:38Z","abstract_excerpt":"Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02136","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":"1612.02136","created_at":"2026-05-18T00:49:41.881021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.02136v5","created_at":"2026-05-18T00:49:41.881021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02136","created_at":"2026-05-18T00:49:41.881021+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V34MZVXN5PT","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V34MZVXN5PTH7RX","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V34MZVX","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2503.04496","citing_title":"Learning to Place Objects with Programs and Iterative Self Training","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16918","citing_title":"HighSync: High-Quality Lip Synchronization via Latent Diffusion Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2506.16255","citing_title":"Category-based Galaxy Image Generation via Diffusion Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2603.21599","citing_title":"Conditional Wasserstein GAN for Simulating Neutrino Event Summaries using Incident Energy of Electron Neutrinos","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU","json":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU.json","graph_json":"https://pith.science/api/pith-number/7V34MZVXN5PTH7RXDT2KAEF5GU/graph.json","events_json":"https://pith.science/api/pith-number/7V34MZVXN5PTH7RXDT2KAEF5GU/events.json","paper":"https://pith.science/paper/7V34MZVX"},"agent_actions":{"view_html":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU","download_json":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU.json","view_paper":"https://pith.science/paper/7V34MZVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.02136&json=true","fetch_graph":"https://pith.science/api/pith-number/7V34MZVXN5PTH7RXDT2KAEF5GU/graph.json","fetch_events":"https://pith.science/api/pith-number/7V34MZVXN5PTH7RXDT2KAEF5GU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU/action/storage_attestation","attest_author":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU/action/author_attestation","sign_citation":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU/action/citation_signature","submit_replication":"https://pith.science/pith/7V34MZVXN5PTH7RXDT2KAEF5GU/action/replication_record"}},"created_at":"2026-05-18T00:49:41.881021+00:00","updated_at":"2026-05-18T00:49:41.881021+00:00"}