{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2EBPGS53TJZ45COJTUGC6FT4XN","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":"ccf97336654664a4bc2719a43d26f34833aabeddffa7b56978e6f2146ea8618d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T16:07:12Z","title_canon_sha256":"a945a022313c5c3496bac58405254991bd8c680aa55642b8450dee2023e38c52"},"schema_version":"1.0","source":{"id":"2505.16839","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16839","created_at":"2026-07-05T11:23:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16839v3","created_at":"2026-07-05T11:23:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16839","created_at":"2026-07-05T11:23:28Z"},{"alias_kind":"pith_short_12","alias_value":"2EBPGS53TJZ4","created_at":"2026-07-05T11:23:28Z"},{"alias_kind":"pith_short_16","alias_value":"2EBPGS53TJZ45COJ","created_at":"2026-07-05T11:23:28Z"},{"alias_kind":"pith_short_8","alias_value":"2EBPGS53","created_at":"2026-07-05T11:23:28Z"}],"graph_snapshots":[{"event_id":"sha256:49e9a0e11cbf7fa6cf177c29462cedd83f8346e322c8c050c836cf668dfc27ab","target":"graph","created_at":"2026-07-05T11:23:28Z","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/2505.16839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere to a desired format). However, existing autoregressive (AR) VLMs like LLaVA struggle in these aspects. Discrete diffusion models (DMs) offer a promising alternative, enabling parallel decoding for faster inference and bidirectional context for controllable generation through text-infilling. While effective in language-only settings, DMs' potential for multi","authors_text":"Aditya Grover, Akash Gokul, Hritik Bansal, Jason Kuen, Kai-Wei Chang, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Zhe Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T16:07:12Z","title":"LaViDa: A Large Diffusion Language Model for Multimodal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16839","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":"sha256:611facc15cbc893e97d10f9adfdbd28becf2c53e413a3eca26a44f59a841f7b6","target":"record","created_at":"2026-07-05T11:23:28Z","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":"ccf97336654664a4bc2719a43d26f34833aabeddffa7b56978e6f2146ea8618d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T16:07:12Z","title_canon_sha256":"a945a022313c5c3496bac58405254991bd8c680aa55642b8450dee2023e38c52"},"schema_version":"1.0","source":{"id":"2505.16839","kind":"arxiv","version":3}},"canonical_sha256":"d102f34bbb9a73ce89c99d0c2f167cbb6239a572b11b76106c421562dacd372c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d102f34bbb9a73ce89c99d0c2f167cbb6239a572b11b76106c421562dacd372c","first_computed_at":"2026-07-05T11:23:28.457929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:28.457929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2yHZE28tABHatTusBMXcCDpQtKE1URpGaFPPqYtPSacRxNCDON+CYU2Dj+BZ7HihKj2PWU59GYunCfbR3GVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:28.458458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16839","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:611facc15cbc893e97d10f9adfdbd28becf2c53e413a3eca26a44f59a841f7b6","sha256:49e9a0e11cbf7fa6cf177c29462cedd83f8346e322c8c050c836cf668dfc27ab"],"state_sha256":"71c10ed0b4dd66ca69a46567d614401b99ad421f042356d4623d1f683517fa7d"}