{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OYQQRJLPSCDMELMEFYKOE72M56","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b7aa54d9dbfcf16eb85ed56a5001e3ca4963d8572a636f3208e70698a88b99bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-25T05:21:59Z","title_canon_sha256":"76779d51c7e6e84205826c8015d6346c9195304b799559905385d608b1bb6932"},"schema_version":"1.0","source":{"id":"2209.12152","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12152","created_at":"2026-07-05T05:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12152v4","created_at":"2026-07-05T05:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12152","created_at":"2026-07-05T05:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"OYQQRJLPSCDM","created_at":"2026-07-05T05:54:31Z"},{"alias_kind":"pith_short_16","alias_value":"OYQQRJLPSCDMELME","created_at":"2026-07-05T05:54:31Z"},{"alias_kind":"pith_short_8","alias_value":"OYQQRJLP","created_at":"2026-07-05T05:54:31Z"}],"graph_snapshots":[{"event_id":"sha256:9448ed15239910523887aa265c04df4d28063ff2d0dd57fa83efcc70a8997340","target":"graph","created_at":"2026-07-05T05:54:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.12152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architecture (named U-ViT) for image generation with diffusion models. U-ViT is characterized by treating all inputs including the time, condition and noisy image patches as tokens and employing long skip connections between shallow and deep layers. We evaluate U-ViT in unconditional and class-conditional image generation, as well as text-to-image generation tasks, where U-ViT is compara","authors_text":"Chongxuan Li, Fan Bao, Hang Su, Jun Zhu, Kaiwen Xue, Shen Nie, Yue Cao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-25T05:21:59Z","title":"All are Worth Words: A ViT Backbone for Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12152","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c998889fb4971a9271fdc628c1c13729ee5eee31ec0f8016e53febc8b77d894","target":"record","created_at":"2026-07-05T05:54:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b7aa54d9dbfcf16eb85ed56a5001e3ca4963d8572a636f3208e70698a88b99bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-25T05:21:59Z","title_canon_sha256":"76779d51c7e6e84205826c8015d6346c9195304b799559905385d608b1bb6932"},"schema_version":"1.0","source":{"id":"2209.12152","kind":"arxiv","version":4}},"canonical_sha256":"762108a56f9086c22d842e14e27f4cef82bcd3ba9995fcd72eec6cf13226c93e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"762108a56f9086c22d842e14e27f4cef82bcd3ba9995fcd72eec6cf13226c93e","first_computed_at":"2026-07-05T05:54:31.432128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:31.432128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C5N+LT/B+BbxFqYIxbFS35rrUyYGdEb6Bf9y72JhGMHIrC3jSZWxU1WBnOTZKknzGDMKk9aBYdj/bDLT2ermAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:31.432611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12152","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c998889fb4971a9271fdc628c1c13729ee5eee31ec0f8016e53febc8b77d894","sha256:9448ed15239910523887aa265c04df4d28063ff2d0dd57fa83efcc70a8997340"],"state_sha256":"b6bb2fdbd4277fdad2fecb778ce45fe9cb6d3f82fe01754b48313461d3c225b5"}