{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PMVYEBDGVIB6C2RACTIXJUSO2N","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":"dc4e0c3aafaab264f1814a4d343f4eb01c528af773c11d02efd4e6354ce4574d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T17:59:41Z","title_canon_sha256":"4acb1d0ce027d111233337f530ee322fa30f818620e5db414745430a4b688298"},"schema_version":"1.0","source":{"id":"2507.10547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10547","created_at":"2026-07-05T11:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10547v1","created_at":"2026-07-05T11:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10547","created_at":"2026-07-05T11:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"PMVYEBDGVIB6","created_at":"2026-07-05T11:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"PMVYEBDGVIB6C2RA","created_at":"2026-07-05T11:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"PMVYEBDG","created_at":"2026-07-05T11:36:53Z"}],"graph_snapshots":[{"event_id":"sha256:f15154740869147a0d193ca96ca0030c3db73458264c7f7b11bab7c96a811aac","target":"graph","created_at":"2026-07-05T11:36:53Z","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/2507.10547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs remains computationally demanding, often necessitating thousands of GPU hours. This work demonstrates that a pre-trained VAE can be efficiently transformed into a VQ-VAE by controlling quantization noise within the VAE's tolerance threshold. We present \\textbf{Quantize-then-Rectify (ReVQ)}, a framework leveraging pre-trained VAEs to enable rapid VQ-VAE training with minimal computational overhead. By integrating \\textbf{","authors_text":"Borui Zhang, Jie Zhou, Jiwen Lu, Qihang Rao, Wenzhao Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T17:59:41Z","title":"Quantize-then-Rectify: Efficient VQ-VAE Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10547","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:ea946fb9f35e7cf4509ff5dc244d40427b28b194b494ec83cdfeded65a66a4b9","target":"record","created_at":"2026-07-05T11:36:53Z","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":"dc4e0c3aafaab264f1814a4d343f4eb01c528af773c11d02efd4e6354ce4574d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T17:59:41Z","title_canon_sha256":"4acb1d0ce027d111233337f530ee322fa30f818620e5db414745430a4b688298"},"schema_version":"1.0","source":{"id":"2507.10547","kind":"arxiv","version":1}},"canonical_sha256":"7b2b820466aa03e16a2014d174d24ed3637baca142b3800656b135c9813846a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b2b820466aa03e16a2014d174d24ed3637baca142b3800656b135c9813846a4","first_computed_at":"2026-07-05T11:36:53.436363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:53.436363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V39vUlbO3fDXLe/N6Hk6L3yu0GyztPya0J/kwu2DA+qfGEQQ+Xi4FsLwBbvRdyvJrTI5NdoJPHqrb/43RBJADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:53.436891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea946fb9f35e7cf4509ff5dc244d40427b28b194b494ec83cdfeded65a66a4b9","sha256:f15154740869147a0d193ca96ca0030c3db73458264c7f7b11bab7c96a811aac"],"state_sha256":"930e7f6e6528062a3357c34661e26a1953ea462bf9ea342e39acdd234f7a71cb"}