{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NE7MOLV7KSWG6M7FFSSR7XEKHQ","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":"884b10394b620000e8e53de086c3329cd4f962b8f5201fd39a85177bdda7e3e4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:40Z","title_canon_sha256":"19b90fdb4eb15ca060e8284380ff6bbbfbb356a736d1c1873d90cffe30c68dee"},"schema_version":"1.0","source":{"id":"2406.10228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10228","created_at":"2026-07-05T08:32:07Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10228v1","created_at":"2026-07-05T08:32:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10228","created_at":"2026-07-05T08:32:07Z"},{"alias_kind":"pith_short_12","alias_value":"NE7MOLV7KSWG","created_at":"2026-07-05T08:32:07Z"},{"alias_kind":"pith_short_16","alias_value":"NE7MOLV7KSWG6M7F","created_at":"2026-07-05T08:32:07Z"},{"alias_kind":"pith_short_8","alias_value":"NE7MOLV7","created_at":"2026-07-05T08:32:07Z"}],"graph_snapshots":[{"event_id":"sha256:63e2c8924d29442bcafd0580b3afb67935cd9956916ba42856e5baa251c444d1","target":"graph","created_at":"2026-07-05T08:32:07Z","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/2406.10228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The swift progress of Multi-modal Large Models (MLLMs) has showcased their impressive ability to tackle tasks blending vision and language. Yet, most current models and benchmarks cater to scenarios with a narrow scope of visual and textual contexts. These models often fall short when faced with complex comprehension tasks, which involve navigating through a plethora of irrelevant and potentially misleading information in both text and image forms. To bridge this gap, we introduce a new, more demanding task known as Interleaved Image-Text Comprehension (IITC). This task challenges models to di","authors_text":"Chaoyou Fu, Chenyu Zhou, Mengdan Zhang, Peixian Chen, Rongrong Ji, Xiawu Zheng, Xing Sun, Yunhang Shen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:40Z","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10228","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":"sha256:243f3261013f1ef1cce5fe80e7bdd9d34dfff6c0ef48e68c61bd10dd047d157b","target":"record","created_at":"2026-07-05T08:32:07Z","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":"884b10394b620000e8e53de086c3329cd4f962b8f5201fd39a85177bdda7e3e4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T17:59:40Z","title_canon_sha256":"19b90fdb4eb15ca060e8284380ff6bbbfbb356a736d1c1873d90cffe30c68dee"},"schema_version":"1.0","source":{"id":"2406.10228","kind":"arxiv","version":1}},"canonical_sha256":"693ec72ebf54ac6f33e52ca51fdc8a3c3cf7d5acd4d4f37e003819660ae948b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"693ec72ebf54ac6f33e52ca51fdc8a3c3cf7d5acd4d4f37e003819660ae948b5","first_computed_at":"2026-07-05T08:32:07.032673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:07.032673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9GR+a4ozoIR2BtQeyYCZbPIh9rfKrTNL2SxDk8UaVqFk7aVCQG/x+5g5cs6zU0gxwEyXhhd3fkzcoLgcXOGXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:07.033171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243f3261013f1ef1cce5fe80e7bdd9d34dfff6c0ef48e68c61bd10dd047d157b","sha256:63e2c8924d29442bcafd0580b3afb67935cd9956916ba42856e5baa251c444d1"],"state_sha256":"6509615d4ee687ea095a3ef430ef6bda352b3ba1b32ddb436a1f61d4b489b925"}