{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5S3JFOXBQP7BN5XT7ASNNCYH36","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":"f4d64699b45efa5c5a279ddaaefd91482a67386b4469aaeab52e1259c6ab9429","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:47Z","title_canon_sha256":"76e828b060e25a4e3536b4f547229952cd8e7529c88b255695f99154e5c29a9b"},"schema_version":"1.0","source":{"id":"2406.11833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11833","created_at":"2026-07-05T09:27:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11833v2","created_at":"2026-07-05T09:27:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11833","created_at":"2026-07-05T09:27:55Z"},{"alias_kind":"pith_short_12","alias_value":"5S3JFOXBQP7B","created_at":"2026-07-05T09:27:55Z"},{"alias_kind":"pith_short_16","alias_value":"5S3JFOXBQP7BN5XT","created_at":"2026-07-05T09:27:55Z"},{"alias_kind":"pith_short_8","alias_value":"5S3JFOXB","created_at":"2026-07-05T09:27:55Z"}],"graph_snapshots":[{"event_id":"sha256:f54602cf1d2957dd18c0d2de3004fa714019ca1e935747eba04ba6cdf58a5830","target":"graph","created_at":"2026-07-05T09:27:55Z","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/2406.11833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Tao Chu, Xiaoyi Dong, Xilin Wei, Yuanjun Xiong, Yuhang Zang, Yu Qiao, Zijian Liang, Ziyu Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:47Z","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11833","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:e563a30387b813ec268a66b9295e805f128292c6028fd08c79f9ec7c52063147","target":"record","created_at":"2026-07-05T09:27:55Z","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":"f4d64699b45efa5c5a279ddaaefd91482a67386b4469aaeab52e1259c6ab9429","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:47Z","title_canon_sha256":"76e828b060e25a4e3536b4f547229952cd8e7529c88b255695f99154e5c29a9b"},"schema_version":"1.0","source":{"id":"2406.11833","kind":"arxiv","version":2}},"canonical_sha256":"ecb692bae183fe16f6f3f824d68b07df82391c17bb0958cad63d65cda571516f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecb692bae183fe16f6f3f824d68b07df82391c17bb0958cad63d65cda571516f","first_computed_at":"2026-07-05T09:27:55.608194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:55.608194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"axcteScCfFWXcNH1axFrNibKGt8auH9aBe8WDmg3LVQoamX4u6uAstySMYBotzgQrpyCj2EjQSBXIfDDzxgBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:55.608734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e563a30387b813ec268a66b9295e805f128292c6028fd08c79f9ec7c52063147","sha256:f54602cf1d2957dd18c0d2de3004fa714019ca1e935747eba04ba6cdf58a5830"],"state_sha256":"27031b98c477f47d96aea4ce2b82a2acefd7152c4ff670c03d440ebd453a5922"}