{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A5YWT5NPNYXLFFO6RCZBDF3ZZW","short_pith_number":"pith:A5YWT5NP","canonical_record":{"source":{"id":"2505.15809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c0d94bf569c6f3f39389aa289310f824ba48a152bb9e854e82bacb938cf3058","abstract_canon_sha256":"9915f21e3ed164bef883cebc22d229638a7cf8d206b66e5fa1e279444700fc8d"},"schema_version":"1.0"},"canonical_sha256":"077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e","source":{"kind":"arxiv","id":"2505.15809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15809","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15809v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15809","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"A5YWT5NPNYXL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"A5YWT5NPNYXLFFO6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"A5YWT5NP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A5YWT5NPNYXLFFO6RCZBDF3ZZW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c0d94bf569c6f3f39389aa289310f824ba48a152bb9e854e82bacb938cf3058","abstract_canon_sha256":"9915f21e3ed164bef883cebc22d229638a7cf8d206b66e5fa1e279444700fc8d"},"schema_version":"1.0"},"canonical_sha256":"077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.312361Z","signature_b64":"YKimGEKH+ucaW8Lxe9DmkMQpn2JrEwXxe4RK4UfKgXaEnPOimhr2Gpm9BeaM08KkMan6+YcepR76c4QK48EaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e","last_reissued_at":"2026-05-17T23:38:52.311878Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.311878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15809","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0pF8V9priGU6otQQtd5vrV9bZeUv+lkr19z55v+1cf5gjmUsv2Y75mbtDpGA+xp59pdQRaKncl0VCI3HmdIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:05:49.080044Z"},"content_sha256":"61a339ebcfd8d892433d3070f256c1633d0bbd5dfd42a5d45b3959da3cd5e86a","schema_version":"1.0","event_id":"sha256:61a339ebcfd8d892433d3070f256c1633d0bbd5dfd42a5d45b3959da3cd5e86a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A5YWT5NPNYXLFFO6RCZBDF3ZZW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMaDA: Multimodal Large Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Li, Ke Shen, Ling Yang, Mengdi Wang, Xinchen Zhang, Ye Tian, Yunhai Tong","submitted_at":"2025-05-21T17:59:05Z","abstract_excerpt":"We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is distinguished by three key innovations: (i) MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components. This architecture ensures seamless integration and processing across different data types. (ii) We implement a mixed long chain-of-thought (CoT)"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The shared probabilistic formulation and modality-agnostic design in the unified diffusion architecture is sufficient to seamlessly integrate and process different data types without modality-specific components.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a88e133fea8857fa0f30815db5e92bd269a2c871019fca0e4649f449dc7b88df"},"source":{"id":"2505.15809","kind":"arxiv","version":2},"verdict":{"id":"9895232e-4f05-421d-b7c2-9de72efa4bbb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:47:07.216120Z","strongest_claim":"MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation.","one_line_summary":"MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The shared probabilistic formulation and modality-agnostic design in the unified diffusion architecture is sufficient to seamlessly integrate and process different data types without modality-specific components.","pith_extraction_headline":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts."},"references":{"count":126,"sample":[{"doi":"","year":2018,"title":"Improving language understanding by generative pre-training","work_id":"72bdd905-4f91-46af-883a-4c2849c99ffd","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Language models are few-shot learners","work_id":"97345cea-ff46-4103-a836-60d34717536c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"OpenAI o1 System Card","work_id":"68d3c334-0fc9-49e3-b7b0-a69afae933e2","ref_index":3,"cited_arxiv_id":"2412.16720","is_internal_anchor":true},{"doi":"","year":2023,"title":"Vl-gpt: A generative pre-trained transformer for vision and language understanding and generation","work_id":"2891128c-bc6e-4651-be44-a7b8f6f3ad91","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Emu: Generative Pretraining in Multimodality","work_id":"d20ff802-68ef-4783-943f-7bf17acb6a68","ref_index":6,"cited_arxiv_id":"2307.05222","is_internal_anchor":true}],"resolved_work":126,"snapshot_sha256":"5250db472d273842a04ea9d80139cfb7ea5056430e1c598a99862e7d69363eed","internal_anchors":32},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb2a8088bfdccd40909723b92584d7d46db4a9731f0e15ca3a443baeb5f5803a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"9895232e-4f05-421d-b7c2-9de72efa4bbb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8rAZlMEVZnlYL/0kY06OaOwnoPXT4Gmw261rZ9QA4pi3/Eg8M1ozB6lakrFWoErIjN5cm8wxGFhVAWMhGBhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:05:49.080577Z"},"content_sha256":"2e99f65d7193bcf234e2eef5159d934de9d111892ad201aa26260e2804896339","schema_version":"1.0","event_id":"sha256:2e99f65d7193bcf234e2eef5159d934de9d111892ad201aa26260e2804896339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/bundle.json","state_url":"https://pith.science/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T19:05:49Z","links":{"resolver":"https://pith.science/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW","bundle":"https://pith.science/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/bundle.json","state":"https://pith.science/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5YWT5NPNYXLFFO6RCZBDF3ZZW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5YWT5NPNYXLFFO6RCZBDF3ZZW","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":"9915f21e3ed164bef883cebc22d229638a7cf8d206b66e5fa1e279444700fc8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:59:05Z","title_canon_sha256":"9c0d94bf569c6f3f39389aa289310f824ba48a152bb9e854e82bacb938cf3058"},"schema_version":"1.0","source":{"id":"2505.15809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15809","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15809v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15809","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"A5YWT5NPNYXL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"A5YWT5NPNYXLFFO6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"A5YWT5NP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2e99f65d7193bcf234e2eef5159d934de9d111892ad201aa26260e2804896339","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The shared probabilistic formulation and modality-agnostic design in the unified diffusion architecture is sufficient to seamlessly integrate and process different data types without modality-specific components."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts."}],"snapshot_sha256":"a88e133fea8857fa0f30815db5e92bd269a2c871019fca0e4649f449dc7b88df"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb2a8088bfdccd40909723b92584d7d46db4a9731f0e15ca3a443baeb5f5803a"},"paper":{"abstract_excerpt":"We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is distinguished by three key innovations: (i) MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components. This architecture ensures seamless integration and processing across different data types. (ii) We implement a mixed long chain-of-thought (CoT)","authors_text":"Bowen Li, Ke Shen, Ling Yang, Mengdi Wang, Xinchen Zhang, Ye Tian, Yunhai Tong","cross_cats":[],"headline":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:59:05Z","title":"MMaDA: Multimodal Large Diffusion Language Models"},"references":{"count":126,"internal_anchors":32,"resolved_work":126,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Improving language understanding by generative pre-training","work_id":"72bdd905-4f91-46af-883a-4c2849c99ffd","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Language models are few-shot learners","work_id":"97345cea-ff46-4103-a836-60d34717536c","year":2020},{"cited_arxiv_id":"2412.16720","doi":"","is_internal_anchor":true,"ref_index":3,"title":"OpenAI o1 System Card","work_id":"68d3c334-0fc9-49e3-b7b0-a69afae933e2","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Vl-gpt: A generative pre-trained transformer for vision and language understanding and generation","work_id":"2891128c-bc6e-4651-be44-a7b8f6f3ad91","year":2023},{"cited_arxiv_id":"2307.05222","doi":"","is_internal_anchor":true,"ref_index":6,"title":"Emu: Generative Pretraining in Multimodality","work_id":"d20ff802-68ef-4783-943f-7bf17acb6a68","year":2023}],"snapshot_sha256":"5250db472d273842a04ea9d80139cfb7ea5056430e1c598a99862e7d69363eed"},"source":{"id":"2505.15809","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T14:47:07.216120Z","id":"9895232e-4f05-421d-b7c2-9de72efa4bbb","model_set":{"reader":"grok-4.3"},"one_line_summary":"MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single diffusion architecture unifies text reasoning, multimodal understanding, and image generation without modality-specific parts.","strongest_claim":"MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation.","weakest_assumption":"The shared probabilistic formulation and modality-agnostic design in the unified diffusion architecture is sufficient to seamlessly integrate and process different data types without modality-specific components."}},"verdict_id":"9895232e-4f05-421d-b7c2-9de72efa4bbb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61a339ebcfd8d892433d3070f256c1633d0bbd5dfd42a5d45b3959da3cd5e86a","target":"record","created_at":"2026-05-17T23:38:52Z","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":"9915f21e3ed164bef883cebc22d229638a7cf8d206b66e5fa1e279444700fc8d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:59:05Z","title_canon_sha256":"9c0d94bf569c6f3f39389aa289310f824ba48a152bb9e854e82bacb938cf3058"},"schema_version":"1.0","source":{"id":"2505.15809","kind":"arxiv","version":2}},"canonical_sha256":"077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077169f5af6e2eb295de88b2119779cd86902265d8155d7d249a5cdc30022e2e","first_computed_at":"2026-05-17T23:38:52.311878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.311878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YKimGEKH+ucaW8Lxe9DmkMQpn2JrEwXxe4RK4UfKgXaEnPOimhr2Gpm9BeaM08KkMan6+YcepR76c4QK48EaDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.312361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61a339ebcfd8d892433d3070f256c1633d0bbd5dfd42a5d45b3959da3cd5e86a","sha256:2e99f65d7193bcf234e2eef5159d934de9d111892ad201aa26260e2804896339"],"state_sha256":"1028e221a06ac28df24e7191fa51c2e235b7a257565f53edbfb4fb92633f0c64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l9E9MJvVcrYwooGnuszypZVyGvZ+BRAZJXuKeokHhK5hGEoxrzPf8u9PkaB0UXYRAmB4dmPciQsOlmS/V/S0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T19:05:49.082931Z","bundle_sha256":"96173a056401bab25c30a94d41826a1395011cb58777354237682d5bb0917db7"}}