{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HNPZY7Z7ZRGOUOP3VRWBAXN7V6","short_pith_number":"pith:HNPZY7Z7","schema_version":"1.0","canonical_sha256":"3b5f9c7f3fcc4cea39fbac6c105dbfafbc44bcfb78cdf40627acf8d277fa740c","source":{"kind":"arxiv","id":"2306.04632","version":1},"attestation_state":"computed","paper":{"title":"Designing a Better Asymmetric VQGAN for StableDiffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Gang Hua, Jianmin Bao, Le Wang, Lu Yuan, Xuelu Feng, Yinpeng Chen, Zixin Zhu","submitted_at":"2023-06-07T17:56:02Z","abstract_excerpt":"StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion model in pixel space, StableDiffusion learns a diffusion model in the latent space via a VQGAN, ensuring both efficiency and quality. It not only supports image generation tasks, but also enables image editing for real images, such as image inpainting and local editing. However, we have observed that the vanilla VQGAN used in StableDiffusion leads to significant information loss, causing distortion artifacts even in no"},"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":"2306.04632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T17:56:02Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"ef1198e274ed9bbe798da39dc9e35fffef69719def1128a3126b7ed6e9753529","abstract_canon_sha256":"df8a872487b9efb329acd31eb2b9b48c2ca8ab6b8caee0c7e22efbdde8548a1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:33.364212Z","signature_b64":"J0cRZegsZC55TkKG6+/AWKEM3BC0WlpygpXs4tqHEaGGmaKJzrz0PkZeFvld4hrQh8kndJxdO15L2ZYcbqOSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5f9c7f3fcc4cea39fbac6c105dbfafbc44bcfb78cdf40627acf8d277fa740c","last_reissued_at":"2026-07-05T06:18:33.363739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:33.363739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing a Better Asymmetric VQGAN for StableDiffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Gang Hua, Jianmin Bao, Le Wang, Lu Yuan, Xuelu Feng, Yinpeng Chen, Zixin Zhu","submitted_at":"2023-06-07T17:56:02Z","abstract_excerpt":"StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion model in pixel space, StableDiffusion learns a diffusion model in the latent space via a VQGAN, ensuring both efficiency and quality. It not only supports image generation tasks, but also enables image editing for real images, such as image inpainting and local editing. However, we have observed that the vanilla VQGAN used in StableDiffusion leads to significant information loss, causing distortion artifacts even in no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04632","kind":"arxiv","version":1},"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/2306.04632/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":"2306.04632","created_at":"2026-07-05T06:18:33.363796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04632v1","created_at":"2026-07-05T06:18:33.363796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04632","created_at":"2026-07-05T06:18:33.363796+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNPZY7Z7ZRGO","created_at":"2026-07-05T06:18:33.363796+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNPZY7Z7ZRGOUOP3","created_at":"2026-07-05T06:18:33.363796+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNPZY7Z7","created_at":"2026-07-05T06:18:33.363796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.02776","citing_title":"XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05960","citing_title":"Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6","json":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6.json","graph_json":"https://pith.science/api/pith-number/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/graph.json","events_json":"https://pith.science/api/pith-number/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/events.json","paper":"https://pith.science/paper/HNPZY7Z7"},"agent_actions":{"view_html":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6","download_json":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6.json","view_paper":"https://pith.science/paper/HNPZY7Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04632&json=true","fetch_graph":"https://pith.science/api/pith-number/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/graph.json","fetch_events":"https://pith.science/api/pith-number/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/action/storage_attestation","attest_author":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/action/author_attestation","sign_citation":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/action/citation_signature","submit_replication":"https://pith.science/pith/HNPZY7Z7ZRGOUOP3VRWBAXN7V6/action/replication_record"}},"created_at":"2026-07-05T06:18:33.363796+00:00","updated_at":"2026-07-05T06:18:33.363796+00:00"}