{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KT77VXKDPWBL4WL6IZHGHKYPW7","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":"e0c37b7be6755e27983ee81192ce1e6fa317d91b88d8ea018849f66ed16d75a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T22:02:21Z","title_canon_sha256":"88a1c695cb079b8af9f8b572064e6215a6aa39da693c7cf71d20b754219a301e"},"schema_version":"1.0","source":{"id":"2504.04633","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04633","created_at":"2026-07-05T11:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04633v3","created_at":"2026-07-05T11:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04633","created_at":"2026-07-05T11:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"KT77VXKDPWBL","created_at":"2026-07-05T11:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"KT77VXKDPWBL4WL6","created_at":"2026-07-05T11:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"KT77VXKD","created_at":"2026-07-05T11:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:74ed69b65d5ee509b96b4996c6167518fff2bb61e26cae177a50c9d148a459fe","target":"graph","created_at":"2026-07-05T11:59:12Z","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/2504.04633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal in-context learning (ICL) equips Large Vision-language Models (LVLMs) with the ability to adapt to new tasks via multiple user-provided demonstrations, without requiring any model parameter updates. However, its effectiveness is constrained by the token-intensive nature of multimodal inputs and the complexity of cross-modal few-shot reasoning, which together hinder LVLMs from extracting useful patterns from demonstrations. To address these challenges, we propose \\textbf{M$^2$IV}, a novel representation engineering approach that replaces explicit token-level demonstrations with a set","authors_text":"Hongyang He, Qisen Cheng, Ruixiang Tang, Tianyang Wang, Xiang Fu, Xi Xiao, Yanshu Li, Yi Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T22:02:21Z","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04633","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":"sha256:81954c0d8bb9ed5be936e27c6eb84b7ff130f85da5f7d0aa4faf14f1f157d2ab","target":"record","created_at":"2026-07-05T11:59:12Z","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":"e0c37b7be6755e27983ee81192ce1e6fa317d91b88d8ea018849f66ed16d75a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T22:02:21Z","title_canon_sha256":"88a1c695cb079b8af9f8b572064e6215a6aa39da693c7cf71d20b754219a301e"},"schema_version":"1.0","source":{"id":"2504.04633","kind":"arxiv","version":3}},"canonical_sha256":"54fffadd437d82be597e464e63ab0fb7d79861743e2ee28834492a00f04e9546","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54fffadd437d82be597e464e63ab0fb7d79861743e2ee28834492a00f04e9546","first_computed_at":"2026-07-05T11:59:12.742351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:12.742351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9UDxroFdL4ZDVbwFT0fBiGEEwLeoF+6c82Yfhe8e8I7INAdZKXY4elcg6EkcYTZCDkUEYrqBDfTLKGqAPvyWBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:12.742795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04633","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81954c0d8bb9ed5be936e27c6eb84b7ff130f85da5f7d0aa4faf14f1f157d2ab","sha256:74ed69b65d5ee509b96b4996c6167518fff2bb61e26cae177a50c9d148a459fe"],"state_sha256":"9a832d51fc74f56eeca42eaee50fdb36cd5024212ec20159f5bffa196cea2699"}