{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:67YTPHNTL6PI2U3GYKVDUEKKL5","short_pith_number":"pith:67YTPHNT","schema_version":"1.0","canonical_sha256":"f7f1379db35f9e8d5366c2aa3a114a5f50d3352c8f3047635193b599502bb36b","source":{"kind":"arxiv","id":"2409.10695","version":2},"attestation_state":"computed","paper":{"title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Aleks Kamko, Alexander Visheratin, Bingchen Liu, Chase Lambert, Daiqing Li, Ehsan Akhgari, Joao Souza, Linmiao Xu, Shivam Shrirao, Suhail Doshi","submitted_at":"2024-09-16T19:52:24Z","abstract_excerpt":"We introduce Playground v3 (PGv3), our latest text-to-image model that achieves state-of-the-art (SoTA) performance across multiple testing benchmarks, excels in graphic design abilities and introduces new capabilities. Unlike traditional text-to-image generative models that rely on pre-trained language models like T5 or CLIP text encoders, our approach fully integrates Large Language Models (LLMs) with a novel structure that leverages text conditions exclusively from a decoder-only LLM. Additionally, to enhance image captioning quality-we developed an in-house captioner, capable of generating"},"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":"2409.10695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T19:52:24Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"7dbfe4f20174b6377a1c6ca4a28d9decb1382dc978837cff3ab1fb80fb13b42f","abstract_canon_sha256":"244a2a681282693152acb976dd42dcb57b984582abd00fb96102b69371b8cd11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:58.984539Z","signature_b64":"xoz/0+CsKCn+e8FBZqrvadgTznjlLJTacTTJXi297DD9bWTqLn6eAw6TEr1vwejlLyPpNsprSEr+jFNvTYXoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7f1379db35f9e8d5366c2aa3a114a5f50d3352c8f3047635193b599502bb36b","last_reissued_at":"2026-07-05T09:23:58.984035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:58.984035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Aleks Kamko, Alexander Visheratin, Bingchen Liu, Chase Lambert, Daiqing Li, Ehsan Akhgari, Joao Souza, Linmiao Xu, Shivam Shrirao, Suhail Doshi","submitted_at":"2024-09-16T19:52:24Z","abstract_excerpt":"We introduce Playground v3 (PGv3), our latest text-to-image model that achieves state-of-the-art (SoTA) performance across multiple testing benchmarks, excels in graphic design abilities and introduces new capabilities. Unlike traditional text-to-image generative models that rely on pre-trained language models like T5 or CLIP text encoders, our approach fully integrates Large Language Models (LLMs) with a novel structure that leverages text conditions exclusively from a decoder-only LLM. Additionally, to enhance image captioning quality-we developed an in-house captioner, capable of generating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10695","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/2409.10695/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":"2409.10695","created_at":"2026-07-05T09:23:58.984095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10695v2","created_at":"2026-07-05T09:23:58.984095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10695","created_at":"2026-07-05T09:23:58.984095+00:00"},{"alias_kind":"pith_short_12","alias_value":"67YTPHNTL6PI","created_at":"2026-07-05T09:23:58.984095+00:00"},{"alias_kind":"pith_short_16","alias_value":"67YTPHNTL6PI2U3G","created_at":"2026-07-05T09:23:58.984095+00:00"},{"alias_kind":"pith_short_8","alias_value":"67YTPHNT","created_at":"2026-07-05T09:23:58.984095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06445","citing_title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24021","citing_title":"Token-to-Token Alignment of Text Embeddings for Semantic Blending","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01803","citing_title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27235","citing_title":"MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2412.00131","citing_title":"Open-Sora Plan: Open-Source Large Video Generation Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":33,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20147","citing_title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14169","citing_title":"Autoregressive Video Generation without Vector Quantization","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20645","citing_title":"PixelDiT: Pixel Diffusion Transformers for Image Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10629","citing_title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03233","citing_title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18869","citing_title":"Emu3: Next-Token Prediction is All You Need","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12322","citing_title":"Self-Adversarial One Step Generation via Condition Shifting","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2410.24164","citing_title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18168","citing_title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5","json":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5.json","graph_json":"https://pith.science/api/pith-number/67YTPHNTL6PI2U3GYKVDUEKKL5/graph.json","events_json":"https://pith.science/api/pith-number/67YTPHNTL6PI2U3GYKVDUEKKL5/events.json","paper":"https://pith.science/paper/67YTPHNT"},"agent_actions":{"view_html":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5","download_json":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5.json","view_paper":"https://pith.science/paper/67YTPHNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10695&json=true","fetch_graph":"https://pith.science/api/pith-number/67YTPHNTL6PI2U3GYKVDUEKKL5/graph.json","fetch_events":"https://pith.science/api/pith-number/67YTPHNTL6PI2U3GYKVDUEKKL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5/action/storage_attestation","attest_author":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5/action/author_attestation","sign_citation":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5/action/citation_signature","submit_replication":"https://pith.science/pith/67YTPHNTL6PI2U3GYKVDUEKKL5/action/replication_record"}},"created_at":"2026-07-05T09:23:58.984095+00:00","updated_at":"2026-07-05T09:23:58.984095+00:00"}