{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UMGUCQAAUWUQZTKX4CDXUVPTWW","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":"370cf5e73d9e5f5b13012a222c1af78758b9b29bac98d764980a7b3a38a2c13c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-20T09:42:43Z","title_canon_sha256":"a726618b82ba81f1506d002ded788a7ead02b365a47e6d077d9b4106244cf629"},"schema_version":"1.0","source":{"id":"2403.13447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13447","created_at":"2026-07-05T07:58:36Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13447v1","created_at":"2026-07-05T07:58:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13447","created_at":"2026-07-05T07:58:36Z"},{"alias_kind":"pith_short_12","alias_value":"UMGUCQAAUWUQ","created_at":"2026-07-05T07:58:36Z"},{"alias_kind":"pith_short_16","alias_value":"UMGUCQAAUWUQZTKX","created_at":"2026-07-05T07:58:36Z"},{"alias_kind":"pith_short_8","alias_value":"UMGUCQAA","created_at":"2026-07-05T07:58:36Z"}],"graph_snapshots":[{"event_id":"sha256:db89b8a702d2e990aa9fb57751bbfd38fbcc33afdbe4dc87c1fe5d1dc351e9a8","target":"graph","created_at":"2026-07-05T07:58:36Z","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/2403.13447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks. The prevailing MLLM paradigm, \\emph{e.g.}, LLaVA, transforms visual features into text-like tokens using a \\emph{static} vision-language mapper, thereby enabling \\emph{static} LLMs to develop the capability to comprehend visual information through visual instruction tuning. Although promising, the \\emph{static} tuning strategy~\\footnote{The static tuning refers to the trained model with static parameters.} that shares the same parameters may con","authors_text":"Fangxun Shu, Hao Jiang, Haoyuan Li, Hao Zhou, He Wanggui, Jiang Liu, Juncheng Li, Lei Zhang, Siliang Tang, Tianwei Lin, Wenqiao Zhang, Yueting Zhuang, Zheqi Lv","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-20T09:42:43Z","title":"HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13447","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":"sha256:4db14a2f96fe9c0d85e0ea0b84e1924840f65b6aac0c5b1fba94fc8a7b83e63e","target":"record","created_at":"2026-07-05T07:58:36Z","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":"370cf5e73d9e5f5b13012a222c1af78758b9b29bac98d764980a7b3a38a2c13c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-20T09:42:43Z","title_canon_sha256":"a726618b82ba81f1506d002ded788a7ead02b365a47e6d077d9b4106244cf629"},"schema_version":"1.0","source":{"id":"2403.13447","kind":"arxiv","version":1}},"canonical_sha256":"a30d414000a5a90ccd57e0877a55f3b5a649ebf59897163541245348f8758941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30d414000a5a90ccd57e0877a55f3b5a649ebf59897163541245348f8758941","first_computed_at":"2026-07-05T07:58:36.758806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:36.758806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ypyAG6BNpgTvS42E+wnUd0ahXuUHn0uQhk8nzEYo7JSXZtRBMJZ7S/FtiamLxCYr7jjeqewqoANmu9M/wXIxAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:36.759349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4db14a2f96fe9c0d85e0ea0b84e1924840f65b6aac0c5b1fba94fc8a7b83e63e","sha256:db89b8a702d2e990aa9fb57751bbfd38fbcc33afdbe4dc87c1fe5d1dc351e9a8"],"state_sha256":"74f66ed9592856b5c64a41f3fa2a4cf50828832c90d5900862deef4522230b77"}