{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YROBJHHESTZQGMBPP6K3EUBMQX","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":"bd67e8c4d74b1af04abf05cc2321368d4fe1e7acd9354635e8d4cc8dc57c9b43","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:57:01Z","title_canon_sha256":"0d265a9f42cc1e601015402b404b4ce0ae06fc78bd0672c8ba58aededf8999e4"},"schema_version":"1.0","source":{"id":"2312.02139","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02139","created_at":"2026-07-05T09:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02139v3","created_at":"2026-07-05T09:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02139","created_at":"2026-07-05T09:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"YROBJHHESTZQ","created_at":"2026-07-05T09:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"YROBJHHESTZQGMBP","created_at":"2026-07-05T09:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"YROBJHHE","created_at":"2026-07-05T09:00:21Z"}],"graph_snapshots":[{"event_id":"sha256:f3f4558a80367ecf58024c4acff4bbfc8a65502a00ed9fb842f0dfa17931a675","target":"graph","created_at":"2026-07-05T09:00:21Z","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/2312.02139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities and scalability, especially for recognition tasks. In this paper, we study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT). Specifically, we propose a methodology for finegrained control of the denoising process and introduce the Time-dependant Multihead Self Attentio","authors_text":"Ali Hatamizadeh, Arash Vahdat, Guilin Liu, Jan Kautz, Jiaming Song","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:57:01Z","title":"DiffiT: Diffusion Vision Transformers for Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02139","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":"sha256:10a58099e2e5b6117d829609497e6a67af5ae9e4d8055caf4330504ce0e8673e","target":"record","created_at":"2026-07-05T09:00:21Z","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":"bd67e8c4d74b1af04abf05cc2321368d4fe1e7acd9354635e8d4cc8dc57c9b43","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:57:01Z","title_canon_sha256":"0d265a9f42cc1e601015402b404b4ce0ae06fc78bd0672c8ba58aededf8999e4"},"schema_version":"1.0","source":{"id":"2312.02139","kind":"arxiv","version":3}},"canonical_sha256":"c45c149ce494f303302f7f95b2502c85e5faf8f416b9b46f9483f83edc984a8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c45c149ce494f303302f7f95b2502c85e5faf8f416b9b46f9483f83edc984a8d","first_computed_at":"2026-07-05T09:00:21.972692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:21.972692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qAyPdf7OdXUqHUmcbnTDl/bCSj2lHQZAb4lvrRWSOF9CjDGy8QWkl9KxrQAOEhSHxK9A8VQj0b9O89TI5uXYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:21.973181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02139","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10a58099e2e5b6117d829609497e6a67af5ae9e4d8055caf4330504ce0e8673e","sha256:f3f4558a80367ecf58024c4acff4bbfc8a65502a00ed9fb842f0dfa17931a675"],"state_sha256":"251302f7f0d59f647442e10f8583d8793a6006635539caf694c8289efbac0107"}