{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XZ5C3FQ4H5LF5SEQVZXOM26DYT","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":"e22e3e97973429ca723b469158967b8d959cd3462f0fe90801193ae7583690a7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T08:12:43Z","title_canon_sha256":"a760bd6b4b331d5f4c3d313e2e8f0fd73098411053cb84d5d59e279a37698377"},"schema_version":"1.0","source":{"id":"2406.07588","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07588","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07588v2","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07588","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_12","alias_value":"XZ5C3FQ4H5LF","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_16","alias_value":"XZ5C3FQ4H5LF5SEQ","created_at":"2026-07-05T08:38:10Z"},{"alias_kind":"pith_short_8","alias_value":"XZ5C3FQ4","created_at":"2026-07-05T08:38:10Z"}],"graph_snapshots":[{"event_id":"sha256:5a4453e2bc6ec5bf57d27f405ef2e1a06c7e742e50312ce16a61b02de7bf601f","target":"graph","created_at":"2026-07-05T08:38:10Z","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/2406.07588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) facilitates Large Language Models (LLMs) exhibiting emergent ability on downstream tasks without updating billions of parameters. However, in the area of multi-modal Large Language Models (MLLMs), two problems hinder the application of multi-modal ICL: (1) Most primary MLLMs are only trained on single-image datasets, making them unable to read multi-modal demonstrations. (2) With the demonstrations increasing, thousands of visual tokens highly challenge hardware and degrade ICL performance. During preliminary explorations, we discovered that the inner LLM tends to foc","authors_text":"Jun Gao, Qian Qiao, Wenjie Li, Zili Wang, Ziqiang Cao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T08:12:43Z","title":"AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07588","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":"sha256:175fe6df0b1b3493ad21dc50a520da2a12ec3da402a88faba36b48f52ce4e71a","target":"record","created_at":"2026-07-05T08:38:10Z","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":"e22e3e97973429ca723b469158967b8d959cd3462f0fe90801193ae7583690a7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T08:12:43Z","title_canon_sha256":"a760bd6b4b331d5f4c3d313e2e8f0fd73098411053cb84d5d59e279a37698377"},"schema_version":"1.0","source":{"id":"2406.07588","kind":"arxiv","version":2}},"canonical_sha256":"be7a2d961c3f565ec890ae6ee66bc3c4df4ad4b997e345d530eb7946ad58b634","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be7a2d961c3f565ec890ae6ee66bc3c4df4ad4b997e345d530eb7946ad58b634","first_computed_at":"2026-07-05T08:38:10.539592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:10.539592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+BzsOrhn/gAd73KZCVw+vQYxcCsGnZ7d7BqpWxejJkmJ0mmVANXSW4/rd9iH4kLLdRQJ9NhihhUSzITrT11KAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:10.540065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07588","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:175fe6df0b1b3493ad21dc50a520da2a12ec3da402a88faba36b48f52ce4e71a","sha256:5a4453e2bc6ec5bf57d27f405ef2e1a06c7e742e50312ce16a61b02de7bf601f"],"state_sha256":"f678838a8211597259b0da5b81f806ccfca90b11090e7b5a0ff3daabe3904912"}