{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GK4TEVBUGQPZUJOTIRKB62I7VQ","short_pith_number":"pith:GK4TEVBU","schema_version":"1.0","canonical_sha256":"32b9325434341f9a25d344541f691fac39fb2f6c7aa44da436674797464d3ef1","source":{"kind":"arxiv","id":"2310.01218","version":1},"attestation_state":"computed","paper":{"title":"Making LLaMA SEE and Draw with SEED Tokenizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Sijie Zhao, Xintao Wang, Ying Shan, Yixiao Ge, Yuying Ge, Ziyun Zeng","submitted_at":"2023-10-02T14:03:02Z","abstract_excerpt":"The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A true AGI agent should not only possess the capability to perform predefined multi-tasks but also exhibit emergent abilities in an open-world context. However, despite the considerable advancements made by recent multimodal LLMs, they still fall short in effectively unifying comprehension and generation tasks, let alone open-world emergent abilities. We contend that the key to overcoming the present impasse lies in enabl"},"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":"2310.01218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T14:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"db3c7182d198a1414acb3203dff67ae29c3f8dc2eef4cab244d2738d005ee646","abstract_canon_sha256":"a44f5fea2e433a1322bcd3050aa848629039e38f699fe0cf393e17d6f160ea4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:24.240704Z","signature_b64":"ts1jT7V+yjHUD6GVfQH5bBCRdRnXSTgqkH6Zmbl+z6ki24wpHch3PUkyE/h1GJphA7nO534gyLHnO1mlgygZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b9325434341f9a25d344541f691fac39fb2f6c7aa44da436674797464d3ef1","last_reissued_at":"2026-07-05T06:56:24.240295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:24.240295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making LLaMA SEE and Draw with SEED Tokenizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Li, Sijie Zhao, Xintao Wang, Ying Shan, Yixiao Ge, Yuying Ge, Ziyun Zeng","submitted_at":"2023-10-02T14:03:02Z","abstract_excerpt":"The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A true AGI agent should not only possess the capability to perform predefined multi-tasks but also exhibit emergent abilities in an open-world context. However, despite the considerable advancements made by recent multimodal LLMs, they still fall short in effectively unifying comprehension and generation tasks, let alone open-world emergent abilities. We contend that the key to overcoming the present impasse lies in enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01218","kind":"arxiv","version":1},"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/2310.01218/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":"2310.01218","created_at":"2026-07-05T06:56:24.240368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01218v1","created_at":"2026-07-05T06:56:24.240368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01218","created_at":"2026-07-05T06:56:24.240368+00:00"},{"alias_kind":"pith_short_12","alias_value":"GK4TEVBUGQPZ","created_at":"2026-07-05T06:56:24.240368+00:00"},{"alias_kind":"pith_short_16","alias_value":"GK4TEVBUGQPZUJOT","created_at":"2026-07-05T06:56:24.240368+00:00"},{"alias_kind":"pith_short_8","alias_value":"GK4TEVBU","created_at":"2026-07-05T06:56:24.240368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07117","citing_title":"Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":253,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13679","citing_title":"InterleaveThinker: Reinforcing Agentic Interleaved Generation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07171","citing_title":"When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":252,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30054","citing_title":"Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14324","citing_title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17726","citing_title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2403.18814","citing_title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21374","citing_title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2407.12772","citing_title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2405.08748","citing_title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12500","citing_title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06525","citing_title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00503","citing_title":"End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ","json":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ.json","graph_json":"https://pith.science/api/pith-number/GK4TEVBUGQPZUJOTIRKB62I7VQ/graph.json","events_json":"https://pith.science/api/pith-number/GK4TEVBUGQPZUJOTIRKB62I7VQ/events.json","paper":"https://pith.science/paper/GK4TEVBU"},"agent_actions":{"view_html":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ","download_json":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ.json","view_paper":"https://pith.science/paper/GK4TEVBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01218&json=true","fetch_graph":"https://pith.science/api/pith-number/GK4TEVBUGQPZUJOTIRKB62I7VQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GK4TEVBUGQPZUJOTIRKB62I7VQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ/action/storage_attestation","attest_author":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ/action/author_attestation","sign_citation":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ/action/citation_signature","submit_replication":"https://pith.science/pith/GK4TEVBUGQPZUJOTIRKB62I7VQ/action/replication_record"}},"created_at":"2026-07-05T06:56:24.240368+00:00","updated_at":"2026-07-05T06:56:24.240368+00:00"}