{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QY2AMIDQFZUKIN6TEZFN4TGKJ5","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":"dca81a58c07cc51de82065ab1301aa0c3cae60b98bba7a2c75b28e48dcd7b5da","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T08:50:45Z","title_canon_sha256":"8ac8ce3aa374bfd1c4e2fe941b5742217e0ebb2795faa0536889c3d2fb0500d1"},"schema_version":"1.0","source":{"id":"2404.15736","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15736","created_at":"2026-07-05T08:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15736v2","created_at":"2026-07-05T08:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15736","created_at":"2026-07-05T08:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"QY2AMIDQFZUK","created_at":"2026-07-05T08:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"QY2AMIDQFZUKIN6T","created_at":"2026-07-05T08:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"QY2AMIDQ","created_at":"2026-07-05T08:12:00Z"}],"graph_snapshots":[{"event_id":"sha256:138b5cfb0f7d17d9c72523ff56e63f6232c42ec1644d5ac6839fa9d8c8772b7c","target":"graph","created_at":"2026-07-05T08:12:00Z","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/2404.15736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples. In this work, we present a comprehensive framework for investigating Multimodal ICL (M-ICL) in the context of Large Multimodal Models. We consider the best open-source multimodal models (e.g., IDEFICS, OpenFlamingo) and a wide range of multimodal tasks. Our study unveils several noteworthy findings: (1) M-ICL primarily relies on text-driven mechanisms, showing little to no influ","authors_text":"Benjamin Piwowarski, Folco Bertini Baldassini, Laure Soulier, Matthieu Cord, Mustafa Shukor","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T08:50:45Z","title":"What Makes Multimodal In-Context Learning Work?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15736","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":"sha256:1e063e13c172d90cc91eaa80ff4bc00ee531216e8760a84d18d103107c2c5596","target":"record","created_at":"2026-07-05T08:12:00Z","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":"dca81a58c07cc51de82065ab1301aa0c3cae60b98bba7a2c75b28e48dcd7b5da","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T08:50:45Z","title_canon_sha256":"8ac8ce3aa374bfd1c4e2fe941b5742217e0ebb2795faa0536889c3d2fb0500d1"},"schema_version":"1.0","source":{"id":"2404.15736","kind":"arxiv","version":2}},"canonical_sha256":"86340620702e68a437d3264ade4cca4f79fc7a811fca920fd791f94a8d900c6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86340620702e68a437d3264ade4cca4f79fc7a811fca920fd791f94a8d900c6e","first_computed_at":"2026-07-05T08:12:00.062631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:00.062631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7aZU67ImDLukMSEYoWC31+tI3WEDe2Xyf0vQPj8Xp8wijzf5SPftJpxeTaIj82iHSqx7l3fOT2PXQGPWd9UBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:00.063074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15736","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e063e13c172d90cc91eaa80ff4bc00ee531216e8760a84d18d103107c2c5596","sha256:138b5cfb0f7d17d9c72523ff56e63f6232c42ec1644d5ac6839fa9d8c8772b7c"],"state_sha256":"e4c8c54678f19f19a364dec0fff7261d95521af9f6d79c25639c18b68b9103cc"}