{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A7BR4SYOUTA2LQIDEHJF6TVK5M","short_pith_number":"pith:A7BR4SYO","schema_version":"1.0","canonical_sha256":"07c31e4b0ea4c1a5c10321d25f4eaaeb22c7da23c7d00dcdb0825a0d8c044821","source":{"kind":"arxiv","id":"2605.17766","version":1},"attestation_state":"computed","paper":{"title":"LatentUMM: Dual Latent Alignment for Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hayes Bai, Jindong Wang, Marios Savvides, Wenwen Wang, Yinyi Luo","submitted_at":"2026-05-18T02:35:05Z","abstract_excerpt":"Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue does not stem from a lack of shared representations, but from the absence of explicit alignment between the transformations that map into and out of the latent space. As a result, generation and re-encoding can follow inconsistent trajectories, leading to semantic drift under modality transitions. In this work, we propose LatentUMM, a framework that construct"},"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":"2605.17766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T02:35:05Z","cross_cats_sorted":[],"title_canon_sha256":"fad020ab4ed61a0c8bb78d1090d906d977d54614106ef884061b9a13b9817008","abstract_canon_sha256":"5d4cc35fc45e4b8dd87bd985b5388a71da86a20bb4818e950a797d5c4d9c0409"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:57.049957Z","signature_b64":"XJ+lEKgfE32QD+QuTWxkbpZl8AM0bEK5fH1uUFutCua6O9xgyyB2CBMKoaAZlapdvedu5G5BD8jxWhioO7zoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07c31e4b0ea4c1a5c10321d25f4eaaeb22c7da23c7d00dcdb0825a0d8c044821","last_reissued_at":"2026-05-20T00:04:57.049153Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:57.049153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LatentUMM: Dual Latent Alignment for Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hayes Bai, Jindong Wang, Marios Savvides, Wenwen Wang, Yinyi Luo","submitted_at":"2026-05-18T02:35:05Z","abstract_excerpt":"Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue does not stem from a lack of shared representations, but from the absence of explicit alignment between the transformations that map into and out of the latent space. As a result, generation and re-encoding can follow inconsistent trajectories, leading to semantic drift under modality transitions. In this work, we propose LatentUMM, a framework that construct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17766","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/2605.17766/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":"2605.17766","created_at":"2026-05-20T00:04:57.049280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17766v1","created_at":"2026-05-20T00:04:57.049280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17766","created_at":"2026-05-20T00:04:57.049280+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7BR4SYOUTA2","created_at":"2026-05-20T00:04:57.049280+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7BR4SYOUTA2LQID","created_at":"2026-05-20T00:04:57.049280+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7BR4SYO","created_at":"2026-05-20T00:04:57.049280+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/A7BR4SYOUTA2LQIDEHJF6TVK5M","json":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M.json","graph_json":"https://pith.science/api/pith-number/A7BR4SYOUTA2LQIDEHJF6TVK5M/graph.json","events_json":"https://pith.science/api/pith-number/A7BR4SYOUTA2LQIDEHJF6TVK5M/events.json","paper":"https://pith.science/paper/A7BR4SYO"},"agent_actions":{"view_html":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M","download_json":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M.json","view_paper":"https://pith.science/paper/A7BR4SYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17766&json=true","fetch_graph":"https://pith.science/api/pith-number/A7BR4SYOUTA2LQIDEHJF6TVK5M/graph.json","fetch_events":"https://pith.science/api/pith-number/A7BR4SYOUTA2LQIDEHJF6TVK5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M/action/storage_attestation","attest_author":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M/action/author_attestation","sign_citation":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M/action/citation_signature","submit_replication":"https://pith.science/pith/A7BR4SYOUTA2LQIDEHJF6TVK5M/action/replication_record"}},"created_at":"2026-05-20T00:04:57.049280+00:00","updated_at":"2026-05-20T00:04:57.049280+00:00"}