{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3GXTHBB6T4ZZVX6GALL6ETGP7L","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":"20cbb9ddced41022e7cd0590b481e875f98ef0e3bd99de5a2f6c5ff1aa21e68d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:08:08Z","title_canon_sha256":"584b9dd86e28f368e897a85232b6bd94c6b29240cb46775bf1860e3752b6e69f"},"schema_version":"1.0","source":{"id":"2506.23639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23639","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23639v1","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23639","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"3GXTHBB6T4ZZ","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"3GXTHBB6T4ZZVX6G","created_at":"2026-07-05T11:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"3GXTHBB6","created_at":"2026-07-05T11:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:7f774538abd41f27aac60e3d86b17579168bc72cf05f34ba21e38415dd9b0d69","target":"graph","created_at":"2026-07-05T11:29:25Z","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/2506.23639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal understanding by applying byte-pair encoding to visual tokens. Unlike conventional approaches that rely on modality-specific encoders, our method directly incorporates structural information into visual tokens, mirroring successful tokenization strategies in text-only language models. We introduce a priority-guided encoding scheme that considers both frequency and s","authors_text":"Hao Luo, Sipeng Zheng, Wanpeng Zhang, Yicheng Feng, Yijiang Li, Zihao Yue, Zongqing Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:08:08Z","title":"Unified Multimodal Understanding via Byte-Pair Visual Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23639","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":"sha256:6cef25e1c02c564580a1148f95cc71f99c81547268b4aba0c3c16bbb286d91f0","target":"record","created_at":"2026-07-05T11:29:25Z","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":"20cbb9ddced41022e7cd0590b481e875f98ef0e3bd99de5a2f6c5ff1aa21e68d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T09:08:08Z","title_canon_sha256":"584b9dd86e28f368e897a85232b6bd94c6b29240cb46775bf1860e3752b6e69f"},"schema_version":"1.0","source":{"id":"2506.23639","kind":"arxiv","version":1}},"canonical_sha256":"d9af33843e9f339adfc602d7e24ccffac6dc7111cf35a2adf3a6598809076590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9af33843e9f339adfc602d7e24ccffac6dc7111cf35a2adf3a6598809076590","first_computed_at":"2026-07-05T11:29:25.510023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:25.510023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3XFPnwW5IdZXT4p4CQnrEcdTmocHV9KcPrK5b3b8O99u4A+kRgSfbTQBGoVYZM4SEdHYO/FhOassoBxUDUNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:25.510530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cef25e1c02c564580a1148f95cc71f99c81547268b4aba0c3c16bbb286d91f0","sha256:7f774538abd41f27aac60e3d86b17579168bc72cf05f34ba21e38415dd9b0d69"],"state_sha256":"a8bd375070729c0c8225d1a1a4d0c59c8eb39cb7b9fd72e87f01195364e8da30"}