{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QDM2HLO2A2TJ5UGXROX4WAOQIP","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":"90885c3d4aa82f22f5c4d1bd52ed62cd7ab1b5afa255e57b5a0cb9faf1cbb0f5","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T07:57:09Z","title_canon_sha256":"dc90809df340d2df5990ac02441c0343eba0f05462e3d8c2f0dd637e20a7a84f"},"schema_version":"1.0","source":{"id":"2506.20214","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20214","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20214v2","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20214","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"QDM2HLO2A2TJ","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_16","alias_value":"QDM2HLO2A2TJ5UGX","created_at":"2026-07-05T11:33:25Z"},{"alias_kind":"pith_short_8","alias_value":"QDM2HLO2","created_at":"2026-07-05T11:33:25Z"}],"graph_snapshots":[{"event_id":"sha256:daa21a44bab440d1d517d6c47bc34a87c2eabd3c878905d80049de7477709e62","target":"graph","created_at":"2026-07-05T11:33:25Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huasong Zhong, Yan Li, Yanzhe Chen (Yen-chieh Chan), Zhenheng Yang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T07:57:09Z","title":"UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20214","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:97d497001d291c603051f59f64692a5d6f0bce2cd18daec71efae9a9e85675c6","target":"record","created_at":"2026-07-05T11:33:25Z","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":"90885c3d4aa82f22f5c4d1bd52ed62cd7ab1b5afa255e57b5a0cb9faf1cbb0f5","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T07:57:09Z","title_canon_sha256":"dc90809df340d2df5990ac02441c0343eba0f05462e3d8c2f0dd637e20a7a84f"},"schema_version":"1.0","source":{"id":"2506.20214","kind":"arxiv","version":2}},"canonical_sha256":"80d9a3adda06a69ed0d78bafcb01d043f16ee1d8334d3e0e5285b8cc2a913eef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80d9a3adda06a69ed0d78bafcb01d043f16ee1d8334d3e0e5285b8cc2a913eef","first_computed_at":"2026-07-05T11:33:25.306727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:25.306727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U8ukPTQJRueb9aNV7mbpy8rkXCvADWUaLZXC064nllsqyutkqi/rCTy/qHVa1XKS3NnZ69+kdDL3I7VHAU+SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:25.307237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20214","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97d497001d291c603051f59f64692a5d6f0bce2cd18daec71efae9a9e85675c6","sha256:daa21a44bab440d1d517d6c47bc34a87c2eabd3c878905d80049de7477709e62"],"state_sha256":"7f642366b9ea5c1ba95c970af77cfc5bd03a3e285839a31b530033124c283713"}