{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KRLXRBPZY7RRJSCZ76GV6XP34D","short_pith_number":"pith:KRLXRBPZ","schema_version":"1.0","canonical_sha256":"54577885f9c7e314c859ff8d5f5dfbe0d954888774bbbe2d0acb442822ca9d1b","source":{"kind":"arxiv","id":"2504.04423","version":1},"attestation_state":"computed","paper":{"title":"UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haibo Qiu, Jingjing Chen, Lin Ma, Shaoxiang Chen, Yang Jiao, Yu-Gang Jiang, Zequn Jie","submitted_at":"2025-04-06T09:20:49Z","abstract_excerpt":"We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth exp"},"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":"2504.04423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T09:20:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b69377910d09054e2ba0b7bdf6f9224d3a4a13564ba68a23dadbc491d0d5e0a3","abstract_canon_sha256":"a51e61db4f8e1e9d65a187ddacafcf4d233c7f5b4e6c798a1cafda3db9a57385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:23.612179Z","signature_b64":"NbYie7d+3r3VOfhQVA9/9DIP23I0sLTxU3UiCZ6b+1jI5BX98puFhZNiIYYr0wID3OKcYFdRrOj5SiURBOctDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54577885f9c7e314c859ff8d5f5dfbe0d954888774bbbe2d0acb442822ca9d1b","last_reissued_at":"2026-07-05T10:45:23.611775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:23.611775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haibo Qiu, Jingjing Chen, Lin Ma, Shaoxiang Chen, Yang Jiao, Yu-Gang Jiang, Zequn Jie","submitted_at":"2025-04-06T09:20:49Z","abstract_excerpt":"We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04423","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/2504.04423/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":"2504.04423","created_at":"2026-07-05T10:45:23.611835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04423v1","created_at":"2026-07-05T10:45:23.611835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04423","created_at":"2026-07-05T10:45:23.611835+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRLXRBPZY7RR","created_at":"2026-07-05T10:45:23.611835+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRLXRBPZY7RRJSCZ","created_at":"2026-07-05T10:45:23.611835+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRLXRBPZ","created_at":"2026-07-05T10:45:23.611835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D","json":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D.json","graph_json":"https://pith.science/api/pith-number/KRLXRBPZY7RRJSCZ76GV6XP34D/graph.json","events_json":"https://pith.science/api/pith-number/KRLXRBPZY7RRJSCZ76GV6XP34D/events.json","paper":"https://pith.science/paper/KRLXRBPZ"},"agent_actions":{"view_html":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D","download_json":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D.json","view_paper":"https://pith.science/paper/KRLXRBPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04423&json=true","fetch_graph":"https://pith.science/api/pith-number/KRLXRBPZY7RRJSCZ76GV6XP34D/graph.json","fetch_events":"https://pith.science/api/pith-number/KRLXRBPZY7RRJSCZ76GV6XP34D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D/action/storage_attestation","attest_author":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D/action/author_attestation","sign_citation":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D/action/citation_signature","submit_replication":"https://pith.science/pith/KRLXRBPZY7RRJSCZ76GV6XP34D/action/replication_record"}},"created_at":"2026-07-05T10:45:23.611835+00:00","updated_at":"2026-07-05T10:45:23.611835+00:00"}