{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YROBJHHESTZQGMBPP6K3EUBMQX","short_pith_number":"pith:YROBJHHE","schema_version":"1.0","canonical_sha256":"c45c149ce494f303302f7f95b2502c85e5faf8f416b9b46f9483f83edc984a8d","source":{"kind":"arxiv","id":"2312.02139","version":3},"attestation_state":"computed","paper":{"title":"DiffiT: Diffusion Vision Transformers for Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Arash Vahdat, Guilin Liu, Jan Kautz, Jiaming Song","submitted_at":"2023-12-04T18:57:01Z","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"},"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":"2312.02139","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T18:57:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0d265a9f42cc1e601015402b404b4ce0ae06fc78bd0672c8ba58aededf8999e4","abstract_canon_sha256":"bd67e8c4d74b1af04abf05cc2321368d4fe1e7acd9354635e8d4cc8dc57c9b43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:21.973181Z","signature_b64":"qAyPdf7OdXUqHUmcbnTDl/bCSj2lHQZAb4lvrRWSOF9CjDGy8QWkl9KxrQAOEhSHxK9A8VQj0b9O89TI5uXYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c45c149ce494f303302f7f95b2502c85e5faf8f416b9b46f9483f83edc984a8d","last_reissued_at":"2026-07-05T09:00:21.972692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:21.972692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffiT: Diffusion Vision Transformers for Image Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Arash Vahdat, Guilin Liu, Jan Kautz, Jiaming Song","submitted_at":"2023-12-04T18:57:01Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02139","kind":"arxiv","version":3},"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/2312.02139/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":"2312.02139","created_at":"2026-07-05T09:00:21.972746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02139v3","created_at":"2026-07-05T09:00:21.972746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02139","created_at":"2026-07-05T09:00:21.972746+00:00"},{"alias_kind":"pith_short_12","alias_value":"YROBJHHESTZQ","created_at":"2026-07-05T09:00:21.972746+00:00"},{"alias_kind":"pith_short_16","alias_value":"YROBJHHESTZQGMBP","created_at":"2026-07-05T09:00:21.972746+00:00"},{"alias_kind":"pith_short_8","alias_value":"YROBJHHE","created_at":"2026-07-05T09:00:21.972746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05135","citing_title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2408.06292","citing_title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX","json":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX.json","graph_json":"https://pith.science/api/pith-number/YROBJHHESTZQGMBPP6K3EUBMQX/graph.json","events_json":"https://pith.science/api/pith-number/YROBJHHESTZQGMBPP6K3EUBMQX/events.json","paper":"https://pith.science/paper/YROBJHHE"},"agent_actions":{"view_html":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX","download_json":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX.json","view_paper":"https://pith.science/paper/YROBJHHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02139&json=true","fetch_graph":"https://pith.science/api/pith-number/YROBJHHESTZQGMBPP6K3EUBMQX/graph.json","fetch_events":"https://pith.science/api/pith-number/YROBJHHESTZQGMBPP6K3EUBMQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX/action/storage_attestation","attest_author":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX/action/author_attestation","sign_citation":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX/action/citation_signature","submit_replication":"https://pith.science/pith/YROBJHHESTZQGMBPP6K3EUBMQX/action/replication_record"}},"created_at":"2026-07-05T09:00:21.972746+00:00","updated_at":"2026-07-05T09:00:21.972746+00:00"}