{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TG3ZPEBZ7DJFD7ONCTKGSWSPQ7","short_pith_number":"pith:TG3ZPEBZ","schema_version":"1.0","canonical_sha256":"99b7979039f8d251fdcd14d4695a4f87c866fc59489f9d56e8a79c56f2125fcd","source":{"kind":"arxiv","id":"2605.18390","version":1},"attestation_state":"computed","paper":{"title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anlin Zheng, Chuofan Ma, Gang Yu, Lanxi Gong, Qi Han, Xiangyu Zhang, Xiaojuan Qi, Xin Wen","submitted_at":"2026-05-18T13:38:43Z","abstract_excerpt":"In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating s"},"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":"2605.18390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:38:43Z","cross_cats_sorted":[],"title_canon_sha256":"95a3e1af392eb57f0efdf22493dd96fcb81dc92617afcfc1b6e11b708af9b4ea","abstract_canon_sha256":"ca55c1b784ed42b5503c5adef3184a3d6ff8f6d19e7eaa9e20ccc4f4250f2c76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:58.461223Z","signature_b64":"pAye7m1ylZ5F5Fq4gIWZZSmkyOh2/8iW/3j3G7tHCkbLzdbFks4uUWjsIv77n/XmFgG8kVqAzEBWDIbBlqY2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99b7979039f8d251fdcd14d4695a4f87c866fc59489f9d56e8a79c56f2125fcd","last_reissued_at":"2026-05-20T00:05:58.460411Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:58.460411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anlin Zheng, Chuofan Ma, Gang Yu, Lanxi Gong, Qi Han, Xiangyu Zhang, Xiaojuan Qi, Xin Wen","submitted_at":"2026-05-18T13:38:43Z","abstract_excerpt":"In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18390","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/2605.18390/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T23:52:11.388800Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T23:50:03.299428Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.758512Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:44.725501Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.743219Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"611826d9639e77329e61d8d4e4ecd8aad9a5e6de3fa6b67764ec17bca66a83ba"},"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":"2605.18390","created_at":"2026-05-20T00:05:58.460520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18390v1","created_at":"2026-05-20T00:05:58.460520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18390","created_at":"2026-05-20T00:05:58.460520+00:00"},{"alias_kind":"pith_short_12","alias_value":"TG3ZPEBZ7DJF","created_at":"2026-05-20T00:05:58.460520+00:00"},{"alias_kind":"pith_short_16","alias_value":"TG3ZPEBZ7DJFD7ON","created_at":"2026-05-20T00:05:58.460520+00:00"},{"alias_kind":"pith_short_8","alias_value":"TG3ZPEBZ","created_at":"2026-05-20T00:05:58.460520+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/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7","json":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7.json","graph_json":"https://pith.science/api/pith-number/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/graph.json","events_json":"https://pith.science/api/pith-number/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/events.json","paper":"https://pith.science/paper/TG3ZPEBZ"},"agent_actions":{"view_html":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7","download_json":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7.json","view_paper":"https://pith.science/paper/TG3ZPEBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18390&json=true","fetch_graph":"https://pith.science/api/pith-number/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/action/storage_attestation","attest_author":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/action/author_attestation","sign_citation":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/action/citation_signature","submit_replication":"https://pith.science/pith/TG3ZPEBZ7DJFD7ONCTKGSWSPQ7/action/replication_record"}},"created_at":"2026-05-20T00:05:58.460520+00:00","updated_at":"2026-05-20T00:05:58.460520+00:00"}