{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYT3MLCNKRFWBHU5CJ7EMRQUEV","short_pith_number":"pith:GYT3MLCN","schema_version":"1.0","canonical_sha256":"3627b62c4d544b609e9d127e464614255cd5c87864ae6313a448b44ff71793cc","source":{"kind":"arxiv","id":"2412.01762","version":1},"attestation_state":"computed","paper":{"title":"XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Hao Chen, Jason Kuen, Jindong Wang, Jiuxiang Gu, Kai Qiu, Xiang Li, Zhe Lin","submitted_at":"2024-12-02T17:58:06Z","abstract_excerpt":"Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture, quantization techniques, and training recipes have significantly enhanced both image reconstruction and the downstream generation quality. In this paper, we present XQ-GAN, an image tokenization framework designed for both image reconstruction and generation tasks. Our framework integrates state-of-the-art quantization techniques, including vector quantization (VQ), re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.01762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T17:58:06Z","cross_cats_sorted":[],"title_canon_sha256":"fe5f690a63cf0a7ede28725b22afba86944ac92231f1c45d43c8dbce7065101a","abstract_canon_sha256":"4eca48a79f0eb78916171ab13347c8bd12520c53b209335168ff12bd9d9d6147"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:19.047988Z","signature_b64":"7cfIEGAtAVnvOUwQUK7uhAJ1OL8uv50CTgKHmSNTkgOsEUHb/plBgRlYp6VCIIPXNrPPHcys+7+TosaAL5CrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3627b62c4d544b609e9d127e464614255cd5c87864ae6313a448b44ff71793cc","last_reissued_at":"2026-07-05T09:43:19.047463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:19.047463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bhiksha Raj, Hao Chen, Jason Kuen, Jindong Wang, Jiuxiang Gu, Kai Qiu, Xiang Li, Zhe Lin","submitted_at":"2024-12-02T17:58:06Z","abstract_excerpt":"Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture, quantization techniques, and training recipes have significantly enhanced both image reconstruction and the downstream generation quality. In this paper, we present XQ-GAN, an image tokenization framework designed for both image reconstruction and generation tasks. Our framework integrates state-of-the-art quantization techniques, including vector quantization (VQ), re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01762","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/2412.01762/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01762","created_at":"2026-07-05T09:43:19.047522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01762v1","created_at":"2026-07-05T09:43:19.047522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01762","created_at":"2026-07-05T09:43:19.047522+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYT3MLCNKRFW","created_at":"2026-07-05T09:43:19.047522+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYT3MLCNKRFWBHU5","created_at":"2026-07-05T09:43:19.047522+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYT3MLCN","created_at":"2026-07-05T09:43:19.047522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31215","citing_title":"Fixed-Point Masked Generative Modeling","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV","json":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV.json","graph_json":"https://pith.science/api/pith-number/GYT3MLCNKRFWBHU5CJ7EMRQUEV/graph.json","events_json":"https://pith.science/api/pith-number/GYT3MLCNKRFWBHU5CJ7EMRQUEV/events.json","paper":"https://pith.science/paper/GYT3MLCN"},"agent_actions":{"view_html":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV","download_json":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV.json","view_paper":"https://pith.science/paper/GYT3MLCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01762&json=true","fetch_graph":"https://pith.science/api/pith-number/GYT3MLCNKRFWBHU5CJ7EMRQUEV/graph.json","fetch_events":"https://pith.science/api/pith-number/GYT3MLCNKRFWBHU5CJ7EMRQUEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV/action/storage_attestation","attest_author":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV/action/author_attestation","sign_citation":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV/action/citation_signature","submit_replication":"https://pith.science/pith/GYT3MLCNKRFWBHU5CJ7EMRQUEV/action/replication_record"}},"created_at":"2026-07-05T09:43:19.047522+00:00","updated_at":"2026-07-05T09:43:19.047522+00:00"}