{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PIQKWCMXOAEQVTJSBT6BQKWLJW","short_pith_number":"pith:PIQKWCMX","canonical_record":{"source":{"id":"2403.09072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:29:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0de8d72ec19fd9047e605ca8fee1fff20e59d5a03dd1f907627d0f9d5984bdf9","abstract_canon_sha256":"c652de1f2da85bffd66abf4d60e7c50352a8b9cffcb0673b9e4d50b4a751edbd"},"schema_version":"1.0"},"canonical_sha256":"7a20ab099770090acd320cfc182acb4da5e241bc2706ddecd463f531b45d4b93","source":{"kind":"arxiv","id":"2403.09072","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09072","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09072v1","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09072","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"PIQKWCMXOAEQ","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"PIQKWCMXOAEQVTJS","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"PIQKWCMX","created_at":"2026-07-05T07:56:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PIQKWCMXOAEQVTJSBT6BQKWLJW","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:29:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0de8d72ec19fd9047e605ca8fee1fff20e59d5a03dd1f907627d0f9d5984bdf9","abstract_canon_sha256":"c652de1f2da85bffd66abf4d60e7c50352a8b9cffcb0673b9e4d50b4a751edbd"},"schema_version":"1.0"},"canonical_sha256":"7a20ab099770090acd320cfc182acb4da5e241bc2706ddecd463f531b45d4b93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:04.942250Z","signature_b64":"CYhgWQeg/k78ks9TPc44YKyMultKJ3aw9wBZgYpGAIgwMfY2atsMWYbPb6braZZxE+k2yxuNoZxJhDuLPHq9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a20ab099770090acd320cfc182acb4da5e241bc2706ddecd463f531b45d4b93","last_reissued_at":"2026-07-05T07:56:04.941777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:04.941777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09072","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5k9E3pcSQxkmXOn46/up1aX+cL6gbZrHV1NX+fej62RU7rwONUfmu74SGDia5zWSQ+HJV3AiMUOrsNE5PGdGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:42:34.844144Z"},"content_sha256":"95be604add394c773263f03bb14e304b2106e97a14d3b5110f6a69077106d32d","schema_version":"1.0","event_id":"sha256:95be604add394c773263f03bb14e304b2106e97a14d3b5110f6a69077106d32d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PIQKWCMXOAEQVTJSBT6BQKWLJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniCode: Learning a Unified Codebook for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohan Zhou, Sipeng Zheng, Ye Wang, Yicheng Feng, Zongqing Lu","submitted_at":"2024-03-14T03:29:58Z","abstract_excerpt":"In this paper, we propose \\textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This innovation addresses a critical limitation in existing MLLMs: their reliance on a text-only codebook, which restricts MLLM's ability to generate images and texts in a multimodal context. Towards this end, we propose a language-driven iterative training paradigm, coupled with an in-context pre-training task we term ``image decompression'', enabling our model to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09072","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/2403.09072/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XOU0rPfEc7uBVu5iRfPR1cMGB9hRg/6AsfAomk9ZRL/CRtgbfkD2AmF1Y8iLjo4NszpsivPTu9Ie2RY2bVhUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:42:34.844692Z"},"content_sha256":"72efd8271f6e103f0ba5f38f2b9f390fafadc75b8f0b901e008cf49cdd6fec87","schema_version":"1.0","event_id":"sha256:72efd8271f6e103f0ba5f38f2b9f390fafadc75b8f0b901e008cf49cdd6fec87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/bundle.json","state_url":"https://pith.science/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/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":"2026-08-07T22:42:34Z","links":{"resolver":"https://pith.science/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW","bundle":"https://pith.science/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/bundle.json","state":"https://pith.science/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PIQKWCMXOAEQVTJSBT6BQKWLJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PIQKWCMXOAEQVTJSBT6BQKWLJW","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":"c652de1f2da85bffd66abf4d60e7c50352a8b9cffcb0673b9e4d50b4a751edbd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:29:58Z","title_canon_sha256":"0de8d72ec19fd9047e605ca8fee1fff20e59d5a03dd1f907627d0f9d5984bdf9"},"schema_version":"1.0","source":{"id":"2403.09072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09072","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09072v1","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09072","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"PIQKWCMXOAEQ","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"PIQKWCMXOAEQVTJS","created_at":"2026-07-05T07:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"PIQKWCMX","created_at":"2026-07-05T07:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:72efd8271f6e103f0ba5f38f2b9f390fafadc75b8f0b901e008cf49cdd6fec87","target":"graph","created_at":"2026-07-05T07:56:04Z","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/2403.09072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose \\textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This innovation addresses a critical limitation in existing MLLMs: their reliance on a text-only codebook, which restricts MLLM's ability to generate images and texts in a multimodal context. Towards this end, we propose a language-driven iterative training paradigm, coupled with an in-context pre-training task we term ``image decompression'', enabling our model to ","authors_text":"Bohan Zhou, Sipeng Zheng, Ye Wang, Yicheng Feng, Zongqing Lu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:29:58Z","title":"UniCode: Learning a Unified Codebook for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09072","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":"sha256:95be604add394c773263f03bb14e304b2106e97a14d3b5110f6a69077106d32d","target":"record","created_at":"2026-07-05T07:56:04Z","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":"c652de1f2da85bffd66abf4d60e7c50352a8b9cffcb0673b9e4d50b4a751edbd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T03:29:58Z","title_canon_sha256":"0de8d72ec19fd9047e605ca8fee1fff20e59d5a03dd1f907627d0f9d5984bdf9"},"schema_version":"1.0","source":{"id":"2403.09072","kind":"arxiv","version":1}},"canonical_sha256":"7a20ab099770090acd320cfc182acb4da5e241bc2706ddecd463f531b45d4b93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a20ab099770090acd320cfc182acb4da5e241bc2706ddecd463f531b45d4b93","first_computed_at":"2026-07-05T07:56:04.941777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:04.941777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CYhgWQeg/k78ks9TPc44YKyMultKJ3aw9wBZgYpGAIgwMfY2atsMWYbPb6braZZxE+k2yxuNoZxJhDuLPHq9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:04.942250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95be604add394c773263f03bb14e304b2106e97a14d3b5110f6a69077106d32d","sha256:72efd8271f6e103f0ba5f38f2b9f390fafadc75b8f0b901e008cf49cdd6fec87"],"state_sha256":"85d1cd4a02ac5b89215dd74458598aa66a005737eb958fd4a1cf855d46e856d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXdlp8CKKMs7J5C/1G+nBZLOlJZ8APzpHLC+f0cZNe1J9H1bgmZ82HQ1plb7I16hFO5yV2o8BHGTrsOen7DkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:42:34.850387Z","bundle_sha256":"4ca910cb9eaafd96e0b36cc4d52884830313c9780550964605d2ed7c0126bb7e"}}