{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:55AZPDC5FJO2GT6RWOEHAJACID","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":"c55e6d90f724dd67753a65aa0550a2eae6907e344bce210778f99b914656fd69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T17:05:46Z","title_canon_sha256":"3cafb88e996340167dcada8c179228a3611097b1ad5b504387c7ba3df93ff6d8"},"schema_version":"1.0","source":{"id":"2509.19244","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.19244","created_at":"2026-07-17T00:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.19244v3","created_at":"2026-07-17T00:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.19244","created_at":"2026-07-17T00:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"55AZPDC5FJO2","created_at":"2026-07-17T00:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"55AZPDC5FJO2GT6R","created_at":"2026-07-17T00:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"55AZPDC5","created_at":"2026-07-17T00:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:cdf29a0e2868509cfcbe99b1f95440666ecdfe446d82b7180d770398d2d95dc0","target":"graph","created_at":"2026-07-17T00:20:40Z","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/2509.19244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported","authors_text":"Aditya Grover, Jason Kuen, Jiuxiang Gu, Kangning Liu, Shufan Li, Zhe Lin, Zijun Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T17:05:46Z","title":"Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.19244","kind":"arxiv","version":3},"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:c2124e87e4a84df6b6600252bc0a2fb5e9d26c87d09ec5981e91804a1f248124","target":"record","created_at":"2026-07-17T00:20:40Z","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":"c55e6d90f724dd67753a65aa0550a2eae6907e344bce210778f99b914656fd69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T17:05:46Z","title_canon_sha256":"3cafb88e996340167dcada8c179228a3611097b1ad5b504387c7ba3df93ff6d8"},"schema_version":"1.0","source":{"id":"2509.19244","kind":"arxiv","version":3}},"canonical_sha256":"ef41978c5d2a5da34fd1b38870240240e027ebbbd36eea91cd43de14dd89efc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef41978c5d2a5da34fd1b38870240240e027ebbbd36eea91cd43de14dd89efc8","first_computed_at":"2026-07-17T00:20:40.803877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:40.803877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZUI6ll55AZx+TbZdWVAa2RGGQaXgaOW2wY8MRuX8gvGU3VnvO6nERNCLF8vUwrDpgW1GvLr6/MrIcEI4eqylAA==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:40.804853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.19244","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2124e87e4a84df6b6600252bc0a2fb5e9d26c87d09ec5981e91804a1f248124","sha256:cdf29a0e2868509cfcbe99b1f95440666ecdfe446d82b7180d770398d2d95dc0"],"state_sha256":"627a3acf033546f66e4918ec73971a9c2b57eba02c873f88e974d12268351856"}