{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YCL5OULBSPL5C7CS6AOGEIL34O","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":"6163dc0c391ea5f9fc999d0970289e08615d4c350a0317017c934ee639f8d282","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:59:53Z","title_canon_sha256":"8cac22b25796bfbafbb66cb3a6108b834050ee6f46d6fc7bef522a9f691263a6"},"schema_version":"1.0","source":{"id":"2411.16681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16681","created_at":"2026-07-05T09:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16681v2","created_at":"2026-07-05T09:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16681","created_at":"2026-07-05T09:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"YCL5OULBSPL5","created_at":"2026-07-05T09:41:04Z"},{"alias_kind":"pith_short_16","alias_value":"YCL5OULBSPL5C7CS","created_at":"2026-07-05T09:41:04Z"},{"alias_kind":"pith_short_8","alias_value":"YCL5OULB","created_at":"2026-07-05T09:41:04Z"}],"graph_snapshots":[{"event_id":"sha256:cbe6d81deeb125c338c20075cf59137a47c5d7532ef58eeb1f7afdfe92331e92","target":"graph","created_at":"2026-07-05T09:41:04Z","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/2411.16681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual tokenizers are fundamental to image generation. They convert visual data into discrete tokens, enabling transformer-based models to excel at image generation. Despite their success, VQ-based tokenizers like VQGAN face significant limitations due to constrained vocabulary sizes. Simply expanding the codebook often leads to training instability and diminishing performance gains, making scalability a critical challenge. In this work, we introduce Factorized Quantization (FQ), a novel approach that revitalizes VQ-based tokenizers by decomposing a large codebook into multiple independent sub","authors_text":"Jianxiong Gao, Mike Zheng Shou, Pichao Wang, Tong He, Zechen Bai, Zheng Zhang, Ziteng Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:59:53Z","title":"Factorized Visual Tokenization and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16681","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":"sha256:9d97458190c2f8ea5219914adefaf6851c0b34e326c2725eef8967b4599597c1","target":"record","created_at":"2026-07-05T09:41:04Z","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":"6163dc0c391ea5f9fc999d0970289e08615d4c350a0317017c934ee639f8d282","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T18:59:53Z","title_canon_sha256":"8cac22b25796bfbafbb66cb3a6108b834050ee6f46d6fc7bef522a9f691263a6"},"schema_version":"1.0","source":{"id":"2411.16681","kind":"arxiv","version":2}},"canonical_sha256":"c097d7516193d7d17c52f01c62217be3b037bc75f5f49da4c2858534ea7e2bfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c097d7516193d7d17c52f01c62217be3b037bc75f5f49da4c2858534ea7e2bfe","first_computed_at":"2026-07-05T09:41:04.570832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:04.570832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aA3X6MgaNTNntfQ+vDgWkYj5DJO+2ri30QziDti9Ci32xGIf2CY5liwUFft6Yxj3oQUWfUCj5tmXqTf7MA6tDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:04.571367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d97458190c2f8ea5219914adefaf6851c0b34e326c2725eef8967b4599597c1","sha256:cbe6d81deeb125c338c20075cf59137a47c5d7532ef58eeb1f7afdfe92331e92"],"state_sha256":"cfe87c73c1ccf56f8d70a6bdaa94861f2f87038d921cdf27771069d3b2c0721b"}