{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OBTD72IROXX4UH4POA3B3GGD54","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":"ed0cb86fb7c7484e7a24286be8b712d5d6f68a2aaba83a7164b94f1ab771bdb2","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T07:14:38Z","title_canon_sha256":"7191b0d73478bef7dd764c31c6c3b26d0f111c7dac3ffe18abe0649958fd95be"},"schema_version":"1.0","source":{"id":"2506.23563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23563","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23563v1","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23563","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_12","alias_value":"OBTD72IROXX4","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_16","alias_value":"OBTD72IROXX4UH4P","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_8","alias_value":"OBTD72IR","created_at":"2026-07-05T11:29:24Z"}],"graph_snapshots":[{"event_id":"sha256:8a2a91db1a2a45734e5bef8fd46391855a2125347a9f2ee41b07201cdefcf52f","target":"graph","created_at":"2026-07-05T11:29:24Z","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/2506.23563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning abilities from three key aspects: (1) lack of difficulty and diversity, (2) susceptibility to guessability and memorization, (3) inadequate assessment of intermediate reasoning steps. To fill this gap, we introduce MMReason, a new benchmark designed to precisely and comprehensively evaluate MLLM long-chain reasoning capability with diverse, open-ended, chal","authors_text":"Dacheng Tao, Huanjin Yao, Jiaxing Huang, Jingyi Zhang, Michael K. Chen, Wei Zhang, Wenhao Wu, Wenjie Zeng, Wenzheng Liu, Xikun Zhang, Yawen Qiu, Yuxin Song","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T07:14:38Z","title":"MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23563","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":"sha256:3591bfde8e5a16ac579a90c2805a4f228fabaa3cd25d8145917ebd61a56d4e77","target":"record","created_at":"2026-07-05T11:29:24Z","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":"ed0cb86fb7c7484e7a24286be8b712d5d6f68a2aaba83a7164b94f1ab771bdb2","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T07:14:38Z","title_canon_sha256":"7191b0d73478bef7dd764c31c6c3b26d0f111c7dac3ffe18abe0649958fd95be"},"schema_version":"1.0","source":{"id":"2506.23563","kind":"arxiv","version":1}},"canonical_sha256":"70663fe91175efca1f8f70361d98c3ef3c14330370b457f3dd8fae9c41a08413","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70663fe91175efca1f8f70361d98c3ef3c14330370b457f3dd8fae9c41a08413","first_computed_at":"2026-07-05T11:29:24.055024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:24.055024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UQ0RoSAZG3RQFiIhqR4bba4dydS/8MA7Vo5MUEU/Z1cHjNfY4nZ9A/gVPB5FvpSAHeKD0gaPEQwnEXDupXKSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:24.055538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3591bfde8e5a16ac579a90c2805a4f228fabaa3cd25d8145917ebd61a56d4e77","sha256:8a2a91db1a2a45734e5bef8fd46391855a2125347a9f2ee41b07201cdefcf52f"],"state_sha256":"98054f58a4d5a5d7e78376d813d2675529c74655630a40f8e4e1257dffded287"}