{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2XMHYYSJJUB3S6TVQ5BPRZZ54O","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":"fa06183244ec52f546f4dbada90a676b523606516517c0d6bc5a5abccef1bba1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T08:06:53Z","title_canon_sha256":"2281394fd5f1c09007bdde8f7464c62717b22b88f58670356df6231796027df3"},"schema_version":"1.0","source":{"id":"2504.05782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05782","created_at":"2026-07-05T10:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05782v1","created_at":"2026-07-05T10:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05782","created_at":"2026-07-05T10:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"2XMHYYSJJUB3","created_at":"2026-07-05T10:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"2XMHYYSJJUB3S6TV","created_at":"2026-07-05T10:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"2XMHYYSJ","created_at":"2026-07-05T10:46:09Z"}],"graph_snapshots":[{"event_id":"sha256:b94654cb16cb9e8b6bacc77557bb7bd7eaf03bc519f8d8c9a9fd671168b758d1","target":"graph","created_at":"2026-07-05T10:46:09Z","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/2504.05782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate. Most existing reasoning benchmarks are constrained by limited data size, narrow domain coverage, and unstructured knowledge distribution. To close these gaps, we introduce MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs vi","authors_text":"Chuanhao Li, Fanrui Zhang, Haoquan Zhang, Jianwen Sun, Jiaxin Ai, Kaipeng Zhang, Kai Wang, Ming Li, Pengfei Zhou, Wangbo Zhao, Wenqi Shao, Xiaofeng Mao, Xiaojun Chang, Xiaopeng Peng, Yang You, Yansheng Qiu, Yukang Feng, Zhaopan Xu, Zhen Li, Zizhen Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T08:06:53Z","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05782","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":"sha256:53eeb7bd0c91c259d44d7f81422f4b71c25bca1a0fbb34f61e143cc8ac1a8f36","target":"record","created_at":"2026-07-05T10:46:09Z","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":"fa06183244ec52f546f4dbada90a676b523606516517c0d6bc5a5abccef1bba1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T08:06:53Z","title_canon_sha256":"2281394fd5f1c09007bdde8f7464c62717b22b88f58670356df6231796027df3"},"schema_version":"1.0","source":{"id":"2504.05782","kind":"arxiv","version":1}},"canonical_sha256":"d5d87c62494d03b97a758742f8e73de387fde11b72c8745ab1b8e2ff21f03ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5d87c62494d03b97a758742f8e73de387fde11b72c8745ab1b8e2ff21f03ab4","first_computed_at":"2026-07-05T10:46:09.656908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:09.656908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zbBEvtkifd1BS6/QECanT/Z6WDu6aHsSp7JyDyNuyPEA9FNMCliielXW8WRUzxvy9KvUtsjUccK9w4Ar5loMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:09.657449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53eeb7bd0c91c259d44d7f81422f4b71c25bca1a0fbb34f61e143cc8ac1a8f36","sha256:b94654cb16cb9e8b6bacc77557bb7bd7eaf03bc519f8d8c9a9fd671168b758d1"],"state_sha256":"4b3340a40720b66cbcbab2c698825c6dbbcca51baeba6cf3c918cbd26ae43bd3"}