{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6GWP6UXDC5DV4LQY24DP3QRZAX","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":"fbdc3d3030e2b1daa756daeef0817e7af17c1fd6456a7dd5a4094fe6b33cff29","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T06:46:55Z","title_canon_sha256":"546d6de98e7823d0cf1656ba78ba9826a8d190c02780b9a1acddbe882068c839"},"schema_version":"1.0","source":{"id":"2412.03069","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03069","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03069v2","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03069","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"6GWP6UXDC5DV","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"6GWP6UXDC5DV4LQY","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"6GWP6UXD","created_at":"2026-07-05T11:49:48Z"}],"graph_snapshots":[{"event_id":"sha256:a70962075fe5ba0f6592cb72594f0b47ec9b84fdf3e2811120b3809e2fbd5a7f","target":"graph","created_at":"2026-07-05T11:49:48Z","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/2412.03069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present TokenFlow, a novel unified image tokenizer that bridges the long-standing gap between multimodal understanding and generation. Prior research attempt to employ a single reconstruction-targeted Vector Quantization (VQ) encoder for unifying these two tasks. We observe that understanding and generation require fundamentally different granularities of visual information. This leads to a critical trade-off, particularly compromising performance in multimodal understanding tasks. TokenFlow addresses this challenge through an innovative dual-codebook architecture that decouples semantic an","authors_text":"Daniel K. Du, Huichao Zhang, Hu Ye, Liao Qu, Xinglong Wu, Xu Wang, Yiheng Liu, Yi Jiang, Yiming Gao, Zehuan Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T06:46:55Z","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03069","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:d7b4ead1c6461959dcdb4e70ba5173286c4ab719c2ed88d773887c18c0347950","target":"record","created_at":"2026-07-05T11:49:48Z","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":"fbdc3d3030e2b1daa756daeef0817e7af17c1fd6456a7dd5a4094fe6b33cff29","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T06:46:55Z","title_canon_sha256":"546d6de98e7823d0cf1656ba78ba9826a8d190c02780b9a1acddbe882068c839"},"schema_version":"1.0","source":{"id":"2412.03069","kind":"arxiv","version":2}},"canonical_sha256":"f1acff52e317475e2e18d706fdc23905e62400e16a1bb1a3a5dd9cf81ae890a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1acff52e317475e2e18d706fdc23905e62400e16a1bb1a3a5dd9cf81ae890a7","first_computed_at":"2026-07-05T11:49:48.461219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:48.461219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5GydUTelCCQOq/P3XYsFW9Wp6W8cMaZ9gMKHhx1vYn26Pb+scYfHsSKhTRTWFXTm2sFeGGApBMZITA//CTPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:48.461690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03069","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7b4ead1c6461959dcdb4e70ba5173286c4ab719c2ed88d773887c18c0347950","sha256:a70962075fe5ba0f6592cb72594f0b47ec9b84fdf3e2811120b3809e2fbd5a7f"],"state_sha256":"c839591b83c6fa807f344e6056a8c27871767cf262d90cec33a4c67428636608"}