{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LS5Q64AGUVPDWM6GUYYBCC2T45","short_pith_number":"pith:LS5Q64AG","schema_version":"1.0","canonical_sha256":"5cbb0f7006a55e3b33c6a630110b53e74e6e14bad3e441b9ce1d69ddcb6cac18","source":{"kind":"arxiv","id":"2206.02262","version":4},"attestation_state":"computed","paper":{"title":"Diffusion-GAN: Training GANs with Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huangjie Zheng, Mingyuan Zhou, Pengcheng He, Weizhu Chen, Zhendong Wang","submitted_at":"2022-06-05T20:45:01Z","abstract_excerpt":"Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each "},"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":"2206.02262","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-05T20:45:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7cc8734804ba650595ac55cf860970bfa001b5d6317cded31747aed83df2e278","abstract_canon_sha256":"935f078495235ce115565c70f4f8cec70a0e2a31dae6e2efe5a00c69cadb2638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:46.203820Z","signature_b64":"v4+KMW8gz3l5NzKKyRUFP8VCRhDRew2hybR7I0skdf4JyLOOP9K2643z3hTrx5Q5+SoacIGxwNCio/U6cbX+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbb0f7006a55e3b33c6a630110b53e74e6e14bad3e441b9ce1d69ddcb6cac18","last_reissued_at":"2026-07-05T06:44:46.203341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:46.203341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-GAN: Training GANs with Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huangjie Zheng, Mingyuan Zhou, Pengcheng He, Weizhu Chen, Zhendong Wang","submitted_at":"2022-06-05T20:45:01Z","abstract_excerpt":"Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02262","kind":"arxiv","version":4},"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/2206.02262/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":"2206.02262","created_at":"2026-07-05T06:44:46.203396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02262v4","created_at":"2026-07-05T06:44:46.203396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02262","created_at":"2026-07-05T06:44:46.203396+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS5Q64AGUVPD","created_at":"2026-07-05T06:44:46.203396+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS5Q64AGUVPDWM6G","created_at":"2026-07-05T06:44:46.203396+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS5Q64AG","created_at":"2026-07-05T06:44:46.203396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06949","citing_title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2211.01095","citing_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2208.06193","citing_title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22379","citing_title":"Efficient Diffusion Distillation via Embedding Loss","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20130","citing_title":"Pairing Regularization for Mitigating Many-to-One Collapse in GANs","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45","json":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45.json","graph_json":"https://pith.science/api/pith-number/LS5Q64AGUVPDWM6GUYYBCC2T45/graph.json","events_json":"https://pith.science/api/pith-number/LS5Q64AGUVPDWM6GUYYBCC2T45/events.json","paper":"https://pith.science/paper/LS5Q64AG"},"agent_actions":{"view_html":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45","download_json":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45.json","view_paper":"https://pith.science/paper/LS5Q64AG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02262&json=true","fetch_graph":"https://pith.science/api/pith-number/LS5Q64AGUVPDWM6GUYYBCC2T45/graph.json","fetch_events":"https://pith.science/api/pith-number/LS5Q64AGUVPDWM6GUYYBCC2T45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45/action/storage_attestation","attest_author":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45/action/author_attestation","sign_citation":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45/action/citation_signature","submit_replication":"https://pith.science/pith/LS5Q64AGUVPDWM6GUYYBCC2T45/action/replication_record"}},"created_at":"2026-07-05T06:44:46.203396+00:00","updated_at":"2026-07-05T06:44:46.203396+00:00"}