{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZPMPJEWYUPS7Y6Q5Y54PEINNSI","short_pith_number":"pith:ZPMPJEWY","schema_version":"1.0","canonical_sha256":"cbd8f492d8a3e5fc7a1dc778f221ad92190fd49703068397e276f1863b57f2b8","source":{"kind":"arxiv","id":"2403.04692","version":2},"attestation_state":"computed","paper":{"title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Enze Xie, Huchuan Lu, Junsong Chen, Lewei Yao, Ping Luo, Xiaozhe Ren, Yue Wu, Zhenguo Li, Zhongdao Wang","submitted_at":"2024-03-07T17:41:37Z","abstract_excerpt":"In this paper, we introduce PixArt-\\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\\Sigma represents a significant advancement over its predecessor, PixArt-\\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term \"weak-to-strong training\". The advancements in PixArt-\\S"},"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":"2403.04692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T17:41:37Z","cross_cats_sorted":[],"title_canon_sha256":"a51abc442e8e1997e7b6df6f2953f19e47c02415e2b87e27088697982e7c6fe0","abstract_canon_sha256":"d35a0fd06d91e7ae949fab60bfde2f08c46a804d5fa5736a4a641d3a29dfe586"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:01.024988Z","signature_b64":"IX1zMvXk1oGuUqFXWFTeN6xARkcWK9dvoay53QsxBiXxbATA1iM4b2OgNxTVjhAm3fqMdC7b6r8GnsR6327xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd8f492d8a3e5fc7a1dc778f221ad92190fd49703068397e276f1863b57f2b8","last_reissued_at":"2026-07-05T07:57:01.024518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:01.024518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Enze Xie, Huchuan Lu, Junsong Chen, Lewei Yao, Ping Luo, Xiaozhe Ren, Yue Wu, Zhenguo Li, Zhongdao Wang","submitted_at":"2024-03-07T17:41:37Z","abstract_excerpt":"In this paper, we introduce PixArt-\\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\\Sigma represents a significant advancement over its predecessor, PixArt-\\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term \"weak-to-strong training\". The advancements in PixArt-\\S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04692","kind":"arxiv","version":2},"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/2403.04692/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":"2403.04692","created_at":"2026-07-05T07:57:01.024575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04692v2","created_at":"2026-07-05T07:57:01.024575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04692","created_at":"2026-07-05T07:57:01.024575+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPMPJEWYUPS7","created_at":"2026-07-05T07:57:01.024575+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPMPJEWYUPS7Y6Q5","created_at":"2026-07-05T07:57:01.024575+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPMPJEWY","created_at":"2026-07-05T07:57:01.024575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18554","citing_title":"Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02090","citing_title":"FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32020","citing_title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25798","citing_title":"DiSC: Resolution-Scalable Acceleration of Diffusion Models by Exploiting Sparsity and Cached Token Reuse with Hash-based Distribution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14430","citing_title":"PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2412.00131","citing_title":"Open-Sora Plan: Open-Source Large Video Generation Model","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22015","citing_title":"ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21272","citing_title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15684","citing_title":"ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09732","citing_title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07119","citing_title":"TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10629","citing_title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06940","citing_title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18869","citing_title":"Emu3: Next-Token Prediction is All You Need","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11934","citing_title":"BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17811","citing_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07879","citing_title":"FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07427","citing_title":"Personalizing Text-to-Image Generation to Individual Taste","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04609","citing_title":"Advancing Aesthetic Image Generation via Composition Transfer","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26348","citing_title":"ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI","json":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI.json","graph_json":"https://pith.science/api/pith-number/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/graph.json","events_json":"https://pith.science/api/pith-number/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/events.json","paper":"https://pith.science/paper/ZPMPJEWY"},"agent_actions":{"view_html":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI","download_json":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI.json","view_paper":"https://pith.science/paper/ZPMPJEWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04692&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/action/storage_attestation","attest_author":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/action/author_attestation","sign_citation":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/action/citation_signature","submit_replication":"https://pith.science/pith/ZPMPJEWYUPS7Y6Q5Y54PEINNSI/action/replication_record"}},"created_at":"2026-07-05T07:57:01.024575+00:00","updated_at":"2026-07-05T07:57:01.024575+00:00"}