{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QDM2HLO2A2TJ5UGXROX4WAOQIP","short_pith_number":"pith:QDM2HLO2","schema_version":"1.0","canonical_sha256":"80d9a3adda06a69ed0d78bafcb01d043f16ee1d8334d3e0e5285b8cc2a913eef","source":{"kind":"arxiv","id":"2506.20214","version":2},"attestation_state":"computed","paper":{"title":"UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Huasong Zhong, Yan Li, Yanzhe Chen (Yen-chieh Chan), Zhenheng Yang","submitted_at":"2025-06-25T07:57:09Z","abstract_excerpt":"Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existing codebook-based methods either rely on small vocabularies (~16K entries) that lack fine-grained semantics or naively scale up, resulting in low token utilization and unstable training. We propose UniCode$^2$, a cascaded codebook framework enabling large-scale, semantically aligned, and stable visual tokenization. By clustering millions of SigLIP sequence embeddings, we build a"},"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":"2506.20214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T07:57:09Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"dc90809df340d2df5990ac02441c0343eba0f05462e3d8c2f0dd637e20a7a84f","abstract_canon_sha256":"90885c3d4aa82f22f5c4d1bd52ed62cd7ab1b5afa255e57b5a0cb9faf1cbb0f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:25.307237Z","signature_b64":"U8ukPTQJRueb9aNV7mbpy8rkXCvADWUaLZXC064nllsqyutkqi/rCTy/qHVa1XKS3NnZ69+kdDL3I7VHAU+SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80d9a3adda06a69ed0d78bafcb01d043f16ee1d8334d3e0e5285b8cc2a913eef","last_reissued_at":"2026-07-05T11:33:25.306727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:25.306727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Huasong Zhong, Yan Li, Yanzhe Chen (Yen-chieh Chan), Zhenheng Yang","submitted_at":"2025-06-25T07:57:09Z","abstract_excerpt":"Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existing codebook-based methods either rely on small vocabularies (~16K entries) that lack fine-grained semantics or naively scale up, resulting in low token utilization and unstable training. We propose UniCode$^2$, a cascaded codebook framework enabling large-scale, semantically aligned, and stable visual tokenization. By clustering millions of SigLIP sequence embeddings, we build a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20214","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/2506.20214/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":"2506.20214","created_at":"2026-07-05T11:33:25.306781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20214v2","created_at":"2026-07-05T11:33:25.306781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20214","created_at":"2026-07-05T11:33:25.306781+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDM2HLO2A2TJ","created_at":"2026-07-05T11:33:25.306781+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDM2HLO2A2TJ5UGX","created_at":"2026-07-05T11:33:25.306781+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDM2HLO2","created_at":"2026-07-05T11:33:25.306781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP","json":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP.json","graph_json":"https://pith.science/api/pith-number/QDM2HLO2A2TJ5UGXROX4WAOQIP/graph.json","events_json":"https://pith.science/api/pith-number/QDM2HLO2A2TJ5UGXROX4WAOQIP/events.json","paper":"https://pith.science/paper/QDM2HLO2"},"agent_actions":{"view_html":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP","download_json":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP.json","view_paper":"https://pith.science/paper/QDM2HLO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20214&json=true","fetch_graph":"https://pith.science/api/pith-number/QDM2HLO2A2TJ5UGXROX4WAOQIP/graph.json","fetch_events":"https://pith.science/api/pith-number/QDM2HLO2A2TJ5UGXROX4WAOQIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP/action/storage_attestation","attest_author":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP/action/author_attestation","sign_citation":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP/action/citation_signature","submit_replication":"https://pith.science/pith/QDM2HLO2A2TJ5UGXROX4WAOQIP/action/replication_record"}},"created_at":"2026-07-05T11:33:25.306781+00:00","updated_at":"2026-07-05T11:33:25.306781+00:00"}