{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G5EM5IWWSC6GM3Y2VGWTGSDUYG","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":"d8ba25a382883b7fa943dcc37f3b10df9695495ef5a1295ceb10c57e17f8f2bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-04T18:27:29Z","title_canon_sha256":"49640a21c97f3e99a4aff2140069cbd864de350e58601017b1c9f0fee3578f16"},"schema_version":"1.0","source":{"id":"2405.02730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02730","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02730v3","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02730","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"G5EM5IWWSC6G","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"G5EM5IWWSC6GM3Y2","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"G5EM5IWW","created_at":"2026-07-05T09:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:2e7e3757ea0b469fb8b27967be74ead6c613fa1bc7af9db5fc601b2934a5fdc0","target":"graph","created_at":"2026-07-05T09:28:30Z","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/2405.02730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net by DiTs and their following improvements is worth rethinking. To this end, we conduct a simple toy experiment by comparing a U-Net architectured DiT with an isotropic one. It turns out that the U-Net architecture only gain a slight advantage amid the U-Net inductive bias, indicating potential redun","authors_text":"Chao Xu, Hanting Chen, Jie Hu, Yuchuan Tian, Yunhe Wang, Zhijun Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-04T18:27:29Z","title":"U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02730","kind":"arxiv","version":3},"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":"sha256:59285dc4c004ec6cfc097654e999fa3d7cfa68d26051e898d49b7532f8049e85","target":"record","created_at":"2026-07-05T09:28:30Z","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":"d8ba25a382883b7fa943dcc37f3b10df9695495ef5a1295ceb10c57e17f8f2bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-04T18:27:29Z","title_canon_sha256":"49640a21c97f3e99a4aff2140069cbd864de350e58601017b1c9f0fee3578f16"},"schema_version":"1.0","source":{"id":"2405.02730","kind":"arxiv","version":3}},"canonical_sha256":"3748cea2d690bc666f1aa9ad334874c18985b5121a921237e11d9e8e516f4391","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3748cea2d690bc666f1aa9ad334874c18985b5121a921237e11d9e8e516f4391","first_computed_at":"2026-07-05T09:28:30.582950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:30.582950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AyYmy+1NAVGNMtxCxNE5w5J+JOUWCyFGX4LKwjnSX9KyXkIsDswmyJsz6xtb2sLonFyfQ2F8de8sTpbc2qbMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:30.583388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59285dc4c004ec6cfc097654e999fa3d7cfa68d26051e898d49b7532f8049e85","sha256:2e7e3757ea0b469fb8b27967be74ead6c613fa1bc7af9db5fc601b2934a5fdc0"],"state_sha256":"e38f78353df05b988e53cfca687a92d820f1d4179065a083c5d26db32bd24fcf"}