{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBCAYKJO5VOKWRW63X5LQ5ORS5","short_pith_number":"pith:MBCAYKJO","schema_version":"1.0","canonical_sha256":"60440c292eed5cab46deddfab875d197767408f81333996b9b278804ead477cc","source":{"kind":"arxiv","id":"2410.20482","version":1},"attestation_state":"computed","paper":{"title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hao Fei, Libo Qin, Min Li, Qiguang Chen, Wanxiang Che, Zhi Chen","submitted_at":"2024-10-27T15:37:51Z","abstract_excerpt":"Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: \"What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction usin"},"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":"2410.20482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:37:51Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8635c1a5c396221d6bcf59bb3ee91d0a7d51a0a1f2bcba4182de99f21154597e","abstract_canon_sha256":"74459932703e3c96029b435491af01c4e31605c31d211c9f0ce8404947edd5e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:45.564708Z","signature_b64":"Lsd9gKejeocKaVcHBZWVKGlM60rECIpldPYc7dwgew8sPx1fVaVqO8FfH8b54B4jbrUHFTeEX5HaP9GVzqCdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60440c292eed5cab46deddfab875d197767408f81333996b9b278804ead477cc","last_reissued_at":"2026-07-05T09:26:45.564178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:45.564178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hao Fei, Libo Qin, Min Li, Qiguang Chen, Wanxiang Che, Zhi Chen","submitted_at":"2024-10-27T15:37:51Z","abstract_excerpt":"Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: \"What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20482","kind":"arxiv","version":1},"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/2410.20482/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":"2410.20482","created_at":"2026-07-05T09:26:45.564246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20482v1","created_at":"2026-07-05T09:26:45.564246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20482","created_at":"2026-07-05T09:26:45.564246+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBCAYKJO5VOK","created_at":"2026-07-05T09:26:45.564246+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBCAYKJO5VOKWRW6","created_at":"2026-07-05T09:26:45.564246+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBCAYKJO","created_at":"2026-07-05T09:26:45.564246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":270,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13403","citing_title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5","json":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5.json","graph_json":"https://pith.science/api/pith-number/MBCAYKJO5VOKWRW63X5LQ5ORS5/graph.json","events_json":"https://pith.science/api/pith-number/MBCAYKJO5VOKWRW63X5LQ5ORS5/events.json","paper":"https://pith.science/paper/MBCAYKJO"},"agent_actions":{"view_html":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5","download_json":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5.json","view_paper":"https://pith.science/paper/MBCAYKJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20482&json=true","fetch_graph":"https://pith.science/api/pith-number/MBCAYKJO5VOKWRW63X5LQ5ORS5/graph.json","fetch_events":"https://pith.science/api/pith-number/MBCAYKJO5VOKWRW63X5LQ5ORS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5/action/storage_attestation","attest_author":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5/action/author_attestation","sign_citation":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5/action/citation_signature","submit_replication":"https://pith.science/pith/MBCAYKJO5VOKWRW63X5LQ5ORS5/action/replication_record"}},"created_at":"2026-07-05T09:26:45.564246+00:00","updated_at":"2026-07-05T09:26:45.564246+00:00"}