{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:64DOGDEFK3TA5TCIRGQEDMJ27I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"383a1662c14100320bd8974f97f5b348213f8aa3636ca3f2270bcc60bca01928","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T00:15:32Z","title_canon_sha256":"09b131ebd99582c6a77e135ee13528254020ebb2875a19070250fb26d0967278"},"schema_version":"1.0","source":{"id":"2506.06952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06952","created_at":"2026-06-19T16:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06952v2","created_at":"2026-06-19T16:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06952","created_at":"2026-06-19T16:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"64DOGDEFK3TA","created_at":"2026-06-19T16:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"64DOGDEFK3TA5TCI","created_at":"2026-06-19T16:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"64DOGDEF","created_at":"2026-06-19T16:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:73bdff06a90f810a5693adfe333c0f9d0448de769282e89fb3b314109cb33c20","target":"graph","created_at":"2026-06-19T16:12:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal foundation models unifying image understanding and generation have opened exciting avenues for tackling a wide range of vision-language tasks within a single framework. Despite progress, existing unified models typically require extensive pretraining and struggle to achieve the same level of performance compared to models dedicated to each task. Additionally, many of these models suffer from slow image generation speeds, limiting their practical deployment in real-time or resource-constrained settings. In this work, we propose Layerwise Timestep-Expert Flow-based ","authors_text":"Ismini Lourentzou, Jiaxin Zhang, Jiuhai Chen, Joy Rimchala, Lifu Huang, Shizhe Diao, Ying Shen, Yuguang Yao, Zhiyang Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T00:15:32Z","title":"LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06952","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9cd1dfc99a80d07dc9d2ce86478b9f65e827837ac8c07278918a6a4b52dcf3cf","target":"record","created_at":"2026-06-19T16:12:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"383a1662c14100320bd8974f97f5b348213f8aa3636ca3f2270bcc60bca01928","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T00:15:32Z","title_canon_sha256":"09b131ebd99582c6a77e135ee13528254020ebb2875a19070250fb26d0967278"},"schema_version":"1.0","source":{"id":"2506.06952","kind":"arxiv","version":2}},"canonical_sha256":"f706e30c8556e60ecc4889a041b13afa119c19cdceed874c1a7f37899fa52486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f706e30c8556e60ecc4889a041b13afa119c19cdceed874c1a7f37899fa52486","first_computed_at":"2026-06-19T16:12:13.936411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:13.936411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mfIfuOPrXfMYPL0vd5a17WkRERtljz/qTLSg0qaKbDpSzB5LyUDLS0tqkmAGfgaGIssAngh1ypnkuK5yu8QFDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:13.936812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cd1dfc99a80d07dc9d2ce86478b9f65e827837ac8c07278918a6a4b52dcf3cf","sha256:73bdff06a90f810a5693adfe333c0f9d0448de769282e89fb3b314109cb33c20"],"state_sha256":"3acf07d1bf92ea7e432b34ebd39444f786f3ff39e6a3cd1a5b4283aef5edbb11"}