{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OYQQRJLPSCDMELMEFYKOE72M56","short_pith_number":"pith:OYQQRJLP","schema_version":"1.0","canonical_sha256":"762108a56f9086c22d842e14e27f4cef82bcd3ba9995fcd72eec6cf13226c93e","source":{"kind":"arxiv","id":"2209.12152","version":4},"attestation_state":"computed","paper":{"title":"All are Worth Words: A ViT Backbone for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Fan Bao, Hang Su, Jun Zhu, Kaiwen Xue, Shen Nie, Yue Cao","submitted_at":"2022-09-25T05:21:59Z","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"},"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":"2209.12152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-25T05:21:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76779d51c7e6e84205826c8015d6346c9195304b799559905385d608b1bb6932","abstract_canon_sha256":"b7aa54d9dbfcf16eb85ed56a5001e3ca4963d8572a636f3208e70698a88b99bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:31.432611Z","signature_b64":"C5N+LT/B+BbxFqYIxbFS35rrUyYGdEb6Bf9y72JhGMHIrC3jSZWxU1WBnOTZKknzGDMKk9aBYdj/bDLT2ermAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762108a56f9086c22d842e14e27f4cef82bcd3ba9995fcd72eec6cf13226c93e","last_reissued_at":"2026-07-05T05:54:31.432128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:31.432128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All are Worth Words: A ViT Backbone for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Fan Bao, Hang Su, Jun Zhu, Kaiwen Xue, Shen Nie, Yue Cao","submitted_at":"2022-09-25T05:21:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12152","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/2209.12152/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":"2209.12152","created_at":"2026-07-05T05:54:31.432194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12152v4","created_at":"2026-07-05T05:54:31.432194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12152","created_at":"2026-07-05T05:54:31.432194+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYQQRJLPSCDM","created_at":"2026-07-05T05:54:31.432194+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYQQRJLPSCDMELME","created_at":"2026-07-05T05:54:31.432194+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYQQRJLP","created_at":"2026-07-05T05:54:31.432194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18603","citing_title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56","json":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56.json","graph_json":"https://pith.science/api/pith-number/OYQQRJLPSCDMELMEFYKOE72M56/graph.json","events_json":"https://pith.science/api/pith-number/OYQQRJLPSCDMELMEFYKOE72M56/events.json","paper":"https://pith.science/paper/OYQQRJLP"},"agent_actions":{"view_html":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56","download_json":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56.json","view_paper":"https://pith.science/paper/OYQQRJLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12152&json=true","fetch_graph":"https://pith.science/api/pith-number/OYQQRJLPSCDMELMEFYKOE72M56/graph.json","fetch_events":"https://pith.science/api/pith-number/OYQQRJLPSCDMELMEFYKOE72M56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56/action/storage_attestation","attest_author":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56/action/author_attestation","sign_citation":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56/action/citation_signature","submit_replication":"https://pith.science/pith/OYQQRJLPSCDMELMEFYKOE72M56/action/replication_record"}},"created_at":"2026-07-05T05:54:31.432194+00:00","updated_at":"2026-07-05T05:54:31.432194+00:00"}