{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWO324FUMHJDFLTPFFIFLT4QFB","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":"3c8b42f4ac67d708298dd26db9cd6b672ae33cef38487dd3a494bbdf2e6a1ec7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:55:23Z","title_canon_sha256":"59c4b32278404fc90b995c2ef337d86a492c55acc112263d824a7bd73b59d7fb"},"schema_version":"1.0","source":{"id":"2506.02308","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02308","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02308v3","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02308","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"XWO324FUMHJD","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"XWO324FUMHJDFLTP","created_at":"2026-07-05T11:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"XWO324FU","created_at":"2026-07-05T11:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:c93229fb4f079eff694f6c27852411b5f1150ec4038ef41e3d79a1e2b2f6980c","target":"graph","created_at":"2026-07-05T11:17:46Z","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/2506.02308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the number of instruction-tuning tasks does not consistently yield better performance. Instead, we observe th","authors_text":"Haofei Yu, Paul Pu Liang, Qi Cao, Xiaojun Shan, Xing Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:55:23Z","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02308","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":"sha256:4bf015bbe298b27646a115d6d7dad1d8bb80e3c751073a894e3991b3ed6a6d31","target":"record","created_at":"2026-07-05T11:17:46Z","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":"3c8b42f4ac67d708298dd26db9cd6b672ae33cef38487dd3a494bbdf2e6a1ec7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:55:23Z","title_canon_sha256":"59c4b32278404fc90b995c2ef337d86a492c55acc112263d824a7bd73b59d7fb"},"schema_version":"1.0","source":{"id":"2506.02308","kind":"arxiv","version":3}},"canonical_sha256":"bd9dbd70b461d232ae6f295055cf90287f9e3524064e8c03e9134a1cc5c8178d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd9dbd70b461d232ae6f295055cf90287f9e3524064e8c03e9134a1cc5c8178d","first_computed_at":"2026-07-05T11:17:46.815636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:46.815636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"40cE4eOlOjpXYAaDQxJ4QgQkpfrZa1/RZatqHpY9L/Ynzul9vPz+pjuyFEya1i9mQ+TXkzUbSs5MmJiSCrmhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:46.816076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02308","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bf015bbe298b27646a115d6d7dad1d8bb80e3c751073a894e3991b3ed6a6d31","sha256:c93229fb4f079eff694f6c27852411b5f1150ec4038ef41e3d79a1e2b2f6980c"],"state_sha256":"fb3c1194fd4415fd131793e491b57fad7000978eae72335f174eb187e47ba7fe"}