{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LBV7BVV5DNO2U4TM3WBDAW375C","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":"7056d72d0a0e4bc38685171bc87b964078f439c63cbc9afddc9f34c2124b6b7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T17:08:18Z","title_canon_sha256":"8ed66211ed0a9f1ba8569bbfa74dafcbccf1cb0a3bf94dde5fa579dc2e7e3b48"},"schema_version":"1.0","source":{"id":"2507.15807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15807","created_at":"2026-07-05T11:49:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15807v2","created_at":"2026-07-05T11:49:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15807","created_at":"2026-07-05T11:49:11Z"},{"alias_kind":"pith_short_12","alias_value":"LBV7BVV5DNO2","created_at":"2026-07-05T11:49:11Z"},{"alias_kind":"pith_short_16","alias_value":"LBV7BVV5DNO2U4TM","created_at":"2026-07-05T11:49:11Z"},{"alias_kind":"pith_short_8","alias_value":"LBV7BVV5","created_at":"2026-07-05T11:49:11Z"}],"graph_snapshots":[{"event_id":"sha256:13bbaf4af1870e534c924e665468e3a2fe17b1559a7b406d4c757861002c0ba2","target":"graph","created_at":"2026-07-05T11:49:11Z","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/2507.15807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs), built on powerful language backbones, have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks from a few multimodal demonstrations consisting of images, questions, and answers. Despite showing noticeable improvement on standard vision-language datasets, current MLLMs struggle to leverage visual information in the demonstrations. Specifically, they tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation. This behavior makes MICL still unimodal and largely re","authors_text":"Daniel Cremers, Jianzhe Liu, Jindong Gu, Philip Torr, Shuo Chen, Volker Tresp, Yan Xia, Zhen Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T17:08:18Z","title":"True Multimodal In-Context Learning Needs Attention to the Visual Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15807","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":"sha256:8ef2b43aa37b37837bed5b0839496399e1f03b638ac35a17a39d64ac1c307383","target":"record","created_at":"2026-07-05T11:49:11Z","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":"7056d72d0a0e4bc38685171bc87b964078f439c63cbc9afddc9f34c2124b6b7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T17:08:18Z","title_canon_sha256":"8ed66211ed0a9f1ba8569bbfa74dafcbccf1cb0a3bf94dde5fa579dc2e7e3b48"},"schema_version":"1.0","source":{"id":"2507.15807","kind":"arxiv","version":2}},"canonical_sha256":"586bf0d6bd1b5daa726cdd82305b7fe8ad72890196389839b3141e2a5b0b7499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"586bf0d6bd1b5daa726cdd82305b7fe8ad72890196389839b3141e2a5b0b7499","first_computed_at":"2026-07-05T11:49:11.660981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:11.660981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wxcPp54sp9mtxXzbxNqyXbTQH2C5QxjKhurOyE1LvbqmttvuK3lJABHRMmEJk6gbRhYNKdTSxCmyxXdQXI1SBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:11.661493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ef2b43aa37b37837bed5b0839496399e1f03b638ac35a17a39d64ac1c307383","sha256:13bbaf4af1870e534c924e665468e3a2fe17b1559a7b406d4c757861002c0ba2"],"state_sha256":"5694c776233f13bc98429a9702d0d4c10454434fc61170ee08397cf372214531"}