{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:S42TU3VNBEEU4D36AE2UU5YM2U","short_pith_number":"pith:S42TU3VN","schema_version":"1.0","canonical_sha256":"97353a6ead09094e0f7e01354a770cd51345ed8a3fc4ceff0e0dd0e4d074691c","source":{"kind":"arxiv","id":"2003.06060","version":3},"attestation_state":"computed","paper":{"title":"Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Larochelle, Jascha Sohl-Dickstein, Liam Paull, Ruixiang Zhang, Tong Che, Yoshua Bengio, Yuan Cao","submitted_at":"2020-03-12T23:33:50Z","abstract_excerpt":"We show that the sum of the implicit generator log-density $\\log p_g$ of a GAN with the logit score of the discriminator defines an energy function which yields the true data density when the generator is imperfect but the discriminator is optimal, thus making it possible to improve on the typical generator (with implicit density $p_g$). To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score. This can be achieved "},"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":"2003.06060","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-12T23:33:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1047aa841f2d243bed0e4c6f89e44f2c2dd70cb30d3f48d006de596af92381cd","abstract_canon_sha256":"d90a916d90ca1439c4e3cf2e534d580c82d69bb0186f400217bb8fa148a33655"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:51.751249Z","signature_b64":"prRXjYH5hSekDe1Rq1mOCuwcL33mygG8yRhoX2oYwMFZEIpsd4lFz7Yry6RyivFTQnEZRHDQ/u12N6+NTktdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97353a6ead09094e0f7e01354a770cd51345ed8a3fc4ceff0e0dd0e4d074691c","last_reissued_at":"2026-07-05T02:55:51.750845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:51.750845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Larochelle, Jascha Sohl-Dickstein, Liam Paull, Ruixiang Zhang, Tong Che, Yoshua Bengio, Yuan Cao","submitted_at":"2020-03-12T23:33:50Z","abstract_excerpt":"We show that the sum of the implicit generator log-density $\\log p_g$ of a GAN with the logit score of the discriminator defines an energy function which yields the true data density when the generator is imperfect but the discriminator is optimal, thus making it possible to improve on the typical generator (with implicit density $p_g$). To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score. This can be achieved "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06060","kind":"arxiv","version":3},"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/2003.06060/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":"2003.06060","created_at":"2026-07-05T02:55:51.750905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06060v3","created_at":"2026-07-05T02:55:51.750905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06060","created_at":"2026-07-05T02:55:51.750905+00:00"},{"alias_kind":"pith_short_12","alias_value":"S42TU3VNBEEU","created_at":"2026-07-05T02:55:51.750905+00:00"},{"alias_kind":"pith_short_16","alias_value":"S42TU3VNBEEU4D36","created_at":"2026-07-05T02:55:51.750905+00:00"},{"alias_kind":"pith_short_8","alias_value":"S42TU3VN","created_at":"2026-07-05T02:55:51.750905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2006.11239","citing_title":"Denoising Diffusion Probabilistic Models","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U","json":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U.json","graph_json":"https://pith.science/api/pith-number/S42TU3VNBEEU4D36AE2UU5YM2U/graph.json","events_json":"https://pith.science/api/pith-number/S42TU3VNBEEU4D36AE2UU5YM2U/events.json","paper":"https://pith.science/paper/S42TU3VN"},"agent_actions":{"view_html":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U","download_json":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U.json","view_paper":"https://pith.science/paper/S42TU3VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06060&json=true","fetch_graph":"https://pith.science/api/pith-number/S42TU3VNBEEU4D36AE2UU5YM2U/graph.json","fetch_events":"https://pith.science/api/pith-number/S42TU3VNBEEU4D36AE2UU5YM2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U/action/storage_attestation","attest_author":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U/action/author_attestation","sign_citation":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U/action/citation_signature","submit_replication":"https://pith.science/pith/S42TU3VNBEEU4D36AE2UU5YM2U/action/replication_record"}},"created_at":"2026-07-05T02:55:51.750905+00:00","updated_at":"2026-07-05T02:55:51.750905+00:00"}