{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5D6NBOWVVAELFYOGC4ZG3BXS6L","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":"9c3b9bbbe875099266571b5b4f9cd2236c62b8d7f16dbc37bd367d523f670988","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:28:32Z","title_canon_sha256":"4c27951db34782545a9605ba27efe71dd1ae4fa9d2989c2aebbff4953bad4f67"},"schema_version":"1.0","source":{"id":"2402.04788","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04788","created_at":"2026-07-05T08:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04788v3","created_at":"2026-07-05T08:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04788","created_at":"2026-07-05T08:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"5D6NBOWVVAEL","created_at":"2026-07-05T08:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"5D6NBOWVVAELFYOG","created_at":"2026-07-05T08:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"5D6NBOWV","created_at":"2026-07-05T08:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:4f628b3d7fa58fa2da575fbad28ae2097f300f467b0d921e61d2b219162d323c","target":"graph","created_at":"2026-07-05T08:30:08Z","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/2402.04788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to the absence of multimodal benchmarks that align with human preferences. Drawing inspiration from the concept of LLM-as-a-Judge within LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities, encompassing three distinct tasks: Scoring Evaluation, Pair Comparison, and ","authors_text":"Dongping Chen, Huichi Zhou, Lichao Sun, Pan Zhou, Qihui Zhang, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yao Wan, Yinuo Liu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:28:32Z","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04788","kind":"arxiv","version":3},"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":"sha256:0dba8372b6a6ca992c3ed21b4fc83dc1ad77111598cd0551f0d2a1dff618b37c","target":"record","created_at":"2026-07-05T08:30:08Z","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":"9c3b9bbbe875099266571b5b4f9cd2236c62b8d7f16dbc37bd367d523f670988","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T12:28:32Z","title_canon_sha256":"4c27951db34782545a9605ba27efe71dd1ae4fa9d2989c2aebbff4953bad4f67"},"schema_version":"1.0","source":{"id":"2402.04788","kind":"arxiv","version":3}},"canonical_sha256":"e8fcd0bad5a808b2e1c617326d86f2f2c992b0c8f8df4b7ac6159d15b14b4091","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8fcd0bad5a808b2e1c617326d86f2f2c992b0c8f8df4b7ac6159d15b14b4091","first_computed_at":"2026-07-05T08:30:08.210537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:08.210537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HbcJxE6O3S2fVfIhheoR4kL41LkaQrMifVmt0yjBSevXcUrQMh+5adingvmkQSFd42KpkDtUiB6ZLvXKSzfRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:08.211023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04788","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dba8372b6a6ca992c3ed21b4fc83dc1ad77111598cd0551f0d2a1dff618b37c","sha256:4f628b3d7fa58fa2da575fbad28ae2097f300f467b0d921e61d2b219162d323c"],"state_sha256":"ddcaaa6361144989f770d39d264315ae68205ebd428442e95acd9f8254645870"}