{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TMM7B6CXLYCFKJHFSEOJFT3T2W","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":"96336dda458b705570a96262cba2e0555047ab1794e55bbd21a174837900473c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T20:09:59Z","title_canon_sha256":"3eaa7bfe00724170f4fb5820718314eb8805d9f5a8e7d1ab591df58b316e4ea1"},"schema_version":"1.0","source":{"id":"2411.10557","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10557","created_at":"2026-07-05T11:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10557v3","created_at":"2026-07-05T11:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10557","created_at":"2026-07-05T11:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"TMM7B6CXLYCF","created_at":"2026-07-05T11:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"TMM7B6CXLYCFKJHF","created_at":"2026-07-05T11:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"TMM7B6CX","created_at":"2026-07-05T11:28:32Z"}],"graph_snapshots":[{"event_id":"sha256:8cba9cded192ea4a21e74590e1b5b4f48fe97699d6098c4bf6aae23d3bba7654","target":"graph","created_at":"2026-07-05T11:28:32Z","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/2411.10557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the importance of each modality in the instruction tuning stage, often using a majority of vision-language data while keeping text-only data limited and fixing mixtures of modalities. By incorporating diverse text-only data in the visual instruction tuning stage, we vary vision-language data in various controlled experiments to investigate the importance of modality i","authors_text":"Beliz Gunel, Chenguang Wang, Dawn Song, Jianhong Tu, Lingjuan Lyu, Michael Bendersky, Nicholas Crispino, Ruoxi Jia, Xin Liu, Zhuohao Ni, Zihao Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T20:09:59Z","title":"MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10557","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":"sha256:5b9dd84cce7e83d35d0f631a92e7bc17ae85f269dbbbff3eb094a9faf1d40de8","target":"record","created_at":"2026-07-05T11:28:32Z","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":"96336dda458b705570a96262cba2e0555047ab1794e55bbd21a174837900473c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T20:09:59Z","title_canon_sha256":"3eaa7bfe00724170f4fb5820718314eb8805d9f5a8e7d1ab591df58b316e4ea1"},"schema_version":"1.0","source":{"id":"2411.10557","kind":"arxiv","version":3}},"canonical_sha256":"9b19f0f8575e045524e5911c92cf73d5bcb858e0dfff1ca70de2f67becb53c07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b19f0f8575e045524e5911c92cf73d5bcb858e0dfff1ca70de2f67becb53c07","first_computed_at":"2026-07-05T11:28:32.393002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:32.393002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YgR+CjYjjc2CWZSe1TVNbJKMrxHFL5pKvR+4vZKiKUjKhHAMnanT+Aaj15d0oNOhi5SuMUtbrirtMv3WuEXrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:32.393508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10557","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b9dd84cce7e83d35d0f631a92e7bc17ae85f269dbbbff3eb094a9faf1d40de8","sha256:8cba9cded192ea4a21e74590e1b5b4f48fe97699d6098c4bf6aae23d3bba7654"],"state_sha256":"17305ea017be1fb8960ffac629e768a747f8f41d4eb3144018a616f61d0c7b23"}