{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JS3MJM26KVFOSYMFQCH674OQPO","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":"16b425f12a615573dd7c23562cb8cbbcbdabaa2db67f357a045fad04cd325622","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T13:05:11Z","title_canon_sha256":"cfad4979c3fa6fac752349f2e128693c5c608cd880626b198c48a832fb0ab522"},"schema_version":"1.0","source":{"id":"2410.16983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16983","created_at":"2026-07-05T09:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16983v1","created_at":"2026-07-05T09:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16983","created_at":"2026-07-05T09:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"JS3MJM26KVFO","created_at":"2026-07-05T09:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"JS3MJM26KVFOSYMF","created_at":"2026-07-05T09:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"JS3MJM26","created_at":"2026-07-05T09:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:e4ef2025df5ac652e5954e271e3a209dd2c94889d66b7b7d4cc4a36ca567d623","target":"graph","created_at":"2026-07-05T09:24:09Z","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/2410.16983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to fluctuate between advanced performance and random guessing. This phenomenon exists in both single-modality (text-only or image-only) and mixed-modality (image-text-pair) contexts. Furthermore, we demonstrate that popular MLLMs pay special attention to certain multimodal context positions, particularly the beginning and end. Leveraging this special attention,","authors_text":"Tong Mo, Weiping Li, Xu Chu, Zhijie Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T13:05:11Z","title":"Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16983","kind":"arxiv","version":1},"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":"sha256:47b5ca171cea9a53729238b33e62c1ca9da9c43994e8dea084ff5422f5a8e1b2","target":"record","created_at":"2026-07-05T09:24:09Z","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":"16b425f12a615573dd7c23562cb8cbbcbdabaa2db67f357a045fad04cd325622","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-22T13:05:11Z","title_canon_sha256":"cfad4979c3fa6fac752349f2e128693c5c608cd880626b198c48a832fb0ab522"},"schema_version":"1.0","source":{"id":"2410.16983","kind":"arxiv","version":1}},"canonical_sha256":"4cb6c4b35e554ae96185808feff1d07b9064972d4c7b0d814ddfd59ae3c36c8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cb6c4b35e554ae96185808feff1d07b9064972d4c7b0d814ddfd59ae3c36c8a","first_computed_at":"2026-07-05T09:24:09.779098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:09.779098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PcpMyiQfLI6b+i0p2pWqRy3w0dxcR6+Zv/A3/HxxwM7wA9OXqoof5nHBNOEgJ8TNEk/jI+8MczJ9YUWaNPjGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:09.779645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47b5ca171cea9a53729238b33e62c1ca9da9c43994e8dea084ff5422f5a8e1b2","sha256:e4ef2025df5ac652e5954e271e3a209dd2c94889d66b7b7d4cc4a36ca567d623"],"state_sha256":"2a09170c3b2fc5729df19f849e973bc02dd55878a513fd898ed2d208303b123a"}