{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q6ZQK4V5ETM4MKVI4MJQTLJ4IM","short_pith_number":"pith:Q6ZQK4V5","schema_version":"1.0","canonical_sha256":"87b30572bd24d9c62aa8e31309ad3c43300905cc18ed18b37783ea8d1a3de72f","source":{"kind":"arxiv","id":"2508.13515","version":2},"attestation_state":"computed","paper":{"title":"2D Gaussians Meet Visual Tokenizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingkai Jia, Qian Zhang, Wei Yin, Wenyu Liu, Xiaolin Hu, Xiaoyang Guo, Xinggang Wang, Yiang Shi","submitted_at":"2025-08-19T05:04:10Z","abstract_excerpt":"The image tokenizer is a critical component in AR image generation, as it determines how rich and structured visual content is encoded into compact representations. Existing quantization-based tokenizers such as VQ-GAN primarily focus on appearance features like texture and color, often neglecting geometric structures due to their patch-based design. In this work, we explored how to incorporate more visual information into the tokenizer and proposed a new framework named Visual Gaussian Quantization (VGQ), a novel tokenizer paradigm that explicitly enhances structural modeling by integrating 2"},"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":"2508.13515","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T05:04:10Z","cross_cats_sorted":[],"title_canon_sha256":"cd50a60a61b3db65894f7ddde2c4758dbc037b0870796039149941b3c4e9968e","abstract_canon_sha256":"b40d58da0a3a5dd3b32c507a950af7615092d8d4cd2d39f7b9d8023a5c8a28b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:23.612774Z","signature_b64":"m9SxswDvEBYL3DohBopiy5BOCVYaAPyXtBAbP+yo2txkLCGdmimck1fTXgw09CR115U4nZFEGv0y8aFQQECoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87b30572bd24d9c62aa8e31309ad3c43300905cc18ed18b37783ea8d1a3de72f","last_reissued_at":"2026-07-05T11:56:23.612280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:23.612280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"2D Gaussians Meet Visual Tokenizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingkai Jia, Qian Zhang, Wei Yin, Wenyu Liu, Xiaolin Hu, Xiaoyang Guo, Xinggang Wang, Yiang Shi","submitted_at":"2025-08-19T05:04:10Z","abstract_excerpt":"The image tokenizer is a critical component in AR image generation, as it determines how rich and structured visual content is encoded into compact representations. Existing quantization-based tokenizers such as VQ-GAN primarily focus on appearance features like texture and color, often neglecting geometric structures due to their patch-based design. In this work, we explored how to incorporate more visual information into the tokenizer and proposed a new framework named Visual Gaussian Quantization (VGQ), a novel tokenizer paradigm that explicitly enhances structural modeling by integrating 2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13515","kind":"arxiv","version":2},"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/2508.13515/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":"2508.13515","created_at":"2026-07-05T11:56:23.612342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13515v2","created_at":"2026-07-05T11:56:23.612342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13515","created_at":"2026-07-05T11:56:23.612342+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6ZQK4V5ETM4","created_at":"2026-07-05T11:56:23.612342+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6ZQK4V5ETM4MKVI","created_at":"2026-07-05T11:56:23.612342+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6ZQK4V5","created_at":"2026-07-05T11:56:23.612342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM","json":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM.json","graph_json":"https://pith.science/api/pith-number/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/graph.json","events_json":"https://pith.science/api/pith-number/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/events.json","paper":"https://pith.science/paper/Q6ZQK4V5"},"agent_actions":{"view_html":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM","download_json":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM.json","view_paper":"https://pith.science/paper/Q6ZQK4V5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13515&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/action/storage_attestation","attest_author":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/action/author_attestation","sign_citation":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/action/citation_signature","submit_replication":"https://pith.science/pith/Q6ZQK4V5ETM4MKVI4MJQTLJ4IM/action/replication_record"}},"created_at":"2026-07-05T11:56:23.612342+00:00","updated_at":"2026-07-05T11:56:23.612342+00:00"}