{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3JX7KDJR4H7FJVE52KPJDS7BON","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":"4ba73d05128ab4dd0c9c6dc59bb4e5af942988c4da7f7ffba1a1c867738d0f62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-01T17:26:02Z","title_canon_sha256":"1565d6a174fb684d5579ccd2b8a08bc1444e92f83973d88f71d810f9707d629b"},"schema_version":"1.0","source":{"id":"2603.01195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.01195","created_at":"2026-06-26T01:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2603.01195v2","created_at":"2026-06-26T01:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01195","created_at":"2026-06-26T01:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"3JX7KDJR4H7F","created_at":"2026-06-26T01:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"3JX7KDJR4H7FJVE5","created_at":"2026-06-26T01:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"3JX7KDJR","created_at":"2026-06-26T01:15:49Z"}],"graph_snapshots":[{"event_id":"sha256:dcdd5bcf39d346bc0020ea5c30d7d3928703a39e0fc07a7bf931df3699deb06d","target":"graph","created_at":"2026-06-26T01:15:49Z","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/2603.01195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of multimodal instruction tuning depends not only on dataset scale, but critically on whether training samples genuinely require visual reasoning. However, existing instruction datasets often contain a substantial portion of visually redundant samples (solvable from text alone), as well as multimodally misaligned supervision that can degrade learning. To address this, we propose VisNec (Visual Necessity Score), a principled data selection framework that measures the marginal contribution of visual input during instruction tuning. By comparing predictive loss with and without ","authors_text":"Bin Ren, Hongyi Cai, Jie Li, Kunyu Peng, Mingkang Dong, Sifan Zhou, Yuqian Fu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-01T17:26:02Z","title":"VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01195","kind":"arxiv","version":2},"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":"sha256:946b8d8be867a4971be9e5fffbac3a96425169c0bc7227a35cacf2aa5a03d6aa","target":"record","created_at":"2026-06-26T01:15:49Z","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":"4ba73d05128ab4dd0c9c6dc59bb4e5af942988c4da7f7ffba1a1c867738d0f62","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-01T17:26:02Z","title_canon_sha256":"1565d6a174fb684d5579ccd2b8a08bc1444e92f83973d88f71d810f9707d629b"},"schema_version":"1.0","source":{"id":"2603.01195","kind":"arxiv","version":2}},"canonical_sha256":"da6ff50d31e1fe54d49dd29e91cbe1734b9553bf19a687d2a44b2fd1002347ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da6ff50d31e1fe54d49dd29e91cbe1734b9553bf19a687d2a44b2fd1002347ae","first_computed_at":"2026-06-26T01:15:49.933705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:49.933705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D3MnmNprQ3c9JRyfujHVxByxOOxsvU72iWrN9ppAB7xU1xnxfhp1KHSB/8JwX86g8ZzEH+ilpwXNYps8cr4WBQ==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:49.934166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.01195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:946b8d8be867a4971be9e5fffbac3a96425169c0bc7227a35cacf2aa5a03d6aa","sha256:dcdd5bcf39d346bc0020ea5c30d7d3928703a39e0fc07a7bf931df3699deb06d"],"state_sha256":"f46953bf36b497cfd2e6c3c945f184a0513800a0cbba8658eec37d82f734e817"}