{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NTYA4MNE6T3UDNCA2BPPRZY6VF","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":"5ecad23218c661e93c43f9cac694dde26d5df88006caf17c4a66bb020fe66005","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T08:16:28Z","title_canon_sha256":"4ce25292a1c0e9fba922b58dc779982cad719ce0acc589e31398874f6515f00b"},"schema_version":"1.0","source":{"id":"2607.26596","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26596","created_at":"2026-07-30T01:21:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26596v1","created_at":"2026-07-30T01:21:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26596","created_at":"2026-07-30T01:21:31Z"},{"alias_kind":"pith_short_12","alias_value":"NTYA4MNE6T3U","created_at":"2026-07-30T01:21:31Z"},{"alias_kind":"pith_short_16","alias_value":"NTYA4MNE6T3UDNCA","created_at":"2026-07-30T01:21:31Z"},{"alias_kind":"pith_short_8","alias_value":"NTYA4MNE","created_at":"2026-07-30T01:21:31Z"}],"graph_snapshots":[{"event_id":"sha256:a17fd0045730ef8cb8a3b6a70c7ae9aa56be60701ac7f40b08722ddc7bfe809a","target":"graph","created_at":"2026-07-30T01:21:31Z","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/2607.26596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture. However, fine-tuning all parameters of these models for visual instruction tuning is computationally expensive and often unnecessary, as the representation requirements for visual and textual tokens diverge significantly in the deeper layers of the network. In this paper, we propose Decoupled Visual Processing (DVP), an efficient training framework that replaces the upper decoder layers of a pretrained LLM with a lightweig","authors_text":"Jianhua Tao, Mingkuan Feng, Zhengqi Wen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T08:16:28Z","title":"Decoupled Visual Processing: Efficient Multimodal Adaptation via Modality-Specific Transformer Substitution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26596","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:f8d9ca8d391e9ba784901cf649a4b25b7c498d4673173f1a8fc3d86a2e509cd8","target":"record","created_at":"2026-07-30T01:21:31Z","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":"5ecad23218c661e93c43f9cac694dde26d5df88006caf17c4a66bb020fe66005","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T08:16:28Z","title_canon_sha256":"4ce25292a1c0e9fba922b58dc779982cad719ce0acc589e31398874f6515f00b"},"schema_version":"1.0","source":{"id":"2607.26596","kind":"arxiv","version":1}},"canonical_sha256":"6cf00e31a4f4f741b440d05ef8e71ea972bdee3862a9a1ac76a7e8f54165e943","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cf00e31a4f4f741b440d05ef8e71ea972bdee3862a9a1ac76a7e8f54165e943","first_computed_at":"2026-07-30T01:21:31.796082Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:21:31.796082Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26596","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8d9ca8d391e9ba784901cf649a4b25b7c498d4673173f1a8fc3d86a2e509cd8","sha256:a17fd0045730ef8cb8a3b6a70c7ae9aa56be60701ac7f40b08722ddc7bfe809a"],"state_sha256":"46ce6204fc564e277f5f6f2a603a26727d2ec5500726b346bb4fbba442258afe"}