{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QY2AMIDQFZUKIN6TEZFN4TGKJ5","short_pith_number":"pith:QY2AMIDQ","schema_version":"1.0","canonical_sha256":"86340620702e68a437d3264ade4cca4f79fc7a811fca920fd791f94a8d900c6e","source":{"kind":"arxiv","id":"2404.15736","version":2},"attestation_state":"computed","paper":{"title":"What Makes Multimodal In-Context Learning Work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Piwowarski, Folco Bertini Baldassini, Laure Soulier, Matthieu Cord, Mustafa Shukor","submitted_at":"2024-04-24T08:50:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.15736","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T08:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ac8ce3aa374bfd1c4e2fe941b5742217e0ebb2795faa0536889c3d2fb0500d1","abstract_canon_sha256":"dca81a58c07cc51de82065ab1301aa0c3cae60b98bba7a2c75b28e48dcd7b5da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:00.063074Z","signature_b64":"k7aZU67ImDLukMSEYoWC31+tI3WEDe2Xyf0vQPj8Xp8wijzf5SPftJpxeTaIj82iHSqx7l3fOT2PXQGPWd9UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86340620702e68a437d3264ade4cca4f79fc7a811fca920fd791f94a8d900c6e","last_reissued_at":"2026-07-05T08:12:00.062631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:00.062631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes Multimodal In-Context Learning Work?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Piwowarski, Folco Bertini Baldassini, Laure Soulier, Matthieu Cord, Mustafa Shukor","submitted_at":"2024-04-24T08:50:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15736","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.15736/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.15736","created_at":"2026-07-05T08:12:00.062686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15736v2","created_at":"2026-07-05T08:12:00.062686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15736","created_at":"2026-07-05T08:12:00.062686+00:00"},{"alias_kind":"pith_short_12","alias_value":"QY2AMIDQFZUK","created_at":"2026-07-05T08:12:00.062686+00:00"},{"alias_kind":"pith_short_16","alias_value":"QY2AMIDQFZUKIN6T","created_at":"2026-07-05T08:12:00.062686+00:00"},{"alias_kind":"pith_short_8","alias_value":"QY2AMIDQ","created_at":"2026-07-05T08:12:00.062686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5","json":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5.json","graph_json":"https://pith.science/api/pith-number/QY2AMIDQFZUKIN6TEZFN4TGKJ5/graph.json","events_json":"https://pith.science/api/pith-number/QY2AMIDQFZUKIN6TEZFN4TGKJ5/events.json","paper":"https://pith.science/paper/QY2AMIDQ"},"agent_actions":{"view_html":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5","download_json":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5.json","view_paper":"https://pith.science/paper/QY2AMIDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15736&json=true","fetch_graph":"https://pith.science/api/pith-number/QY2AMIDQFZUKIN6TEZFN4TGKJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/QY2AMIDQFZUKIN6TEZFN4TGKJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5/action/storage_attestation","attest_author":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5/action/author_attestation","sign_citation":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5/action/citation_signature","submit_replication":"https://pith.science/pith/QY2AMIDQFZUKIN6TEZFN4TGKJ5/action/replication_record"}},"created_at":"2026-07-05T08:12:00.062686+00:00","updated_at":"2026-07-05T08:12:00.062686+00:00"}