{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E6NRZPWISU54PGZSHC5D32ILCL","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":"7e62615e10fb260528dc74e6b8f2ff123aa91c511e4dabf6ccd3572e6b9aa6e4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T17:00:44Z","title_canon_sha256":"4cb639cdfa14fad5e2271801fd9063c7ab82f0bf19af318f338b18aceda1614e"},"schema_version":"1.0","source":{"id":"2508.09945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09945","created_at":"2026-07-05T11:53:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09945v1","created_at":"2026-07-05T11:53:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09945","created_at":"2026-07-05T11:53:24Z"},{"alias_kind":"pith_short_12","alias_value":"E6NRZPWISU54","created_at":"2026-07-05T11:53:24Z"},{"alias_kind":"pith_short_16","alias_value":"E6NRZPWISU54PGZS","created_at":"2026-07-05T11:53:24Z"},{"alias_kind":"pith_short_8","alias_value":"E6NRZPWI","created_at":"2026-07-05T11:53:24Z"}],"graph_snapshots":[{"event_id":"sha256:9433f893cfbe93ccbfa16f47516bfa2565720ca513698d7fa4734112b4bb4a5c","target":"graph","created_at":"2026-07-05T11:53:24Z","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/2508.09945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a unified framework that seamlessly merges vision and coding language models to empower MLLMs with strong multimodal code generation abilities. Leveraging a task vector-based model merging technique, we integrate a state-of-the-art coding LLM into a strong vision-language backbone, while preserving both visual comprehension and advanced coding skills. To supp","authors_text":"Dongdong Zhang, Furu Wei, Lingjie Jiang, Shaohan Huang, Xun Wu, Yixia Li","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T17:00:44Z","title":"VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09945","kind":"arxiv","version":1},"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":"sha256:57929fa6d6ecfc00f2ed34cd98908e13e208d3c70e555cad3a6ad9cbae083cc4","target":"record","created_at":"2026-07-05T11:53:24Z","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":"7e62615e10fb260528dc74e6b8f2ff123aa91c511e4dabf6ccd3572e6b9aa6e4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T17:00:44Z","title_canon_sha256":"4cb639cdfa14fad5e2271801fd9063c7ab82f0bf19af318f338b18aceda1614e"},"schema_version":"1.0","source":{"id":"2508.09945","kind":"arxiv","version":1}},"canonical_sha256":"279b1cbec8953bc79b3238ba3de90b12c525e59886e8661b9a8533097fb9f696","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"279b1cbec8953bc79b3238ba3de90b12c525e59886e8661b9a8533097fb9f696","first_computed_at":"2026-07-05T11:53:24.932732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:24.932732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvJUgzXlEoBuOxe3MA3ZoX51dCkJZidvh/6dNFJjnPZx1f3gTnueGBUNSkglhymXdXIShOu8vTiTFaKNE8QIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:24.933234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57929fa6d6ecfc00f2ed34cd98908e13e208d3c70e555cad3a6ad9cbae083cc4","sha256:9433f893cfbe93ccbfa16f47516bfa2565720ca513698d7fa4734112b4bb4a5c"],"state_sha256":"bbbf66dfe5836e96a57f06572de023dede6d7a5abf4a04cce5e3c657d1cf3a99"}