{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R5H7DXU56JNBXNHDN5W6Q3DMRL","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":"829f3a2feda957234a6ae875a98019d944cf8e7931788adaa32fb9165cd7444f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T17:11:50Z","title_canon_sha256":"6f012f516a5ff2c8ec8f3933d4afac5f2c4093a92c352e5401af321fa1035d6b"},"schema_version":"1.0","source":{"id":"2412.06673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06673","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06673v1","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06673","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"R5H7DXU56JNB","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_16","alias_value":"R5H7DXU56JNBXNHD","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_8","alias_value":"R5H7DXU5","created_at":"2026-07-05T09:46:36Z"}],"graph_snapshots":[{"event_id":"sha256:cb977998769659f3bde092f1f4e82a6f163c6b230727e59eb7e59d5f13da7348","target":"graph","created_at":"2026-07-05T09:46:36Z","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/2412.06673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token prediction formulation. To address the large dataset size typically required for image-text alignment, we propose to enhance data efficiency through the design of a vision tokenizer that incorporates semantic information and a progressive multi-stage training procedure. This approach reduces the dataset size to just 15M for pretraining -- over four times fewer than w","authors_text":"Chunwei Wang, Guansong Lu, Hang Xu, Jianhua Han, Junwei Yang, Lu Hou, Runhui Huang, Wei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T17:11:50Z","title":"ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06673","kind":"arxiv","version":1},"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:e60db964dda9c8d0f2ea67a46723d04ce5ce30d6f9ac1734fc21dcd0460a0a5e","target":"record","created_at":"2026-07-05T09:46:36Z","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":"829f3a2feda957234a6ae875a98019d944cf8e7931788adaa32fb9165cd7444f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T17:11:50Z","title_canon_sha256":"6f012f516a5ff2c8ec8f3933d4afac5f2c4093a92c352e5401af321fa1035d6b"},"schema_version":"1.0","source":{"id":"2412.06673","kind":"arxiv","version":1}},"canonical_sha256":"8f4ff1de9df25a1bb4e36f6de86c6c8affa9fd855c5548811da710d8e6fde225","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f4ff1de9df25a1bb4e36f6de86c6c8affa9fd855c5548811da710d8e6fde225","first_computed_at":"2026-07-05T09:46:36.189890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:36.189890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mRgp85qpPNWv3nnuNETifzwP9RBKRhs4sJqqh01VmEgwIJUR3sV3zMskdR3b8FfoSkb+tofg4I6urN9q1U7/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:36.190398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e60db964dda9c8d0f2ea67a46723d04ce5ce30d6f9ac1734fc21dcd0460a0a5e","sha256:cb977998769659f3bde092f1f4e82a6f163c6b230727e59eb7e59d5f13da7348"],"state_sha256":"2b8d46c87eb798e09b24c167d6af4969a5e8bd2199db5abeab6b06a564b88e31"}