{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLX66F36EN5SKKKGPJ5VR2XGVB","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":"eee371575000dce57e80b68203a00ce5765a1a0d374b49c863543044a188708c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T11:41:19Z","title_canon_sha256":"cbe52123a492e087d8a8947eacd9cd8a857a5d662dc26fae0ec24390a235eaf8"},"schema_version":"1.0","source":{"id":"2505.11141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11141","created_at":"2026-07-05T11:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11141v2","created_at":"2026-07-05T11:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11141","created_at":"2026-07-05T11:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"VLX66F36EN5S","created_at":"2026-07-05T11:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"VLX66F36EN5SKKKG","created_at":"2026-07-05T11:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"VLX66F36","created_at":"2026-07-05T11:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:6b76199a9cb744c524edd4deb504f2b4935d759984fd220495096195e880c853","target":"graph","created_at":"2026-07-05T11:08:41Z","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/2505.11141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large language models (LLMs) with human-like reasoning capabilities exhibit exceptional performance and are being gradually integrated into multimodal large language models (MLLMs). However, whether these models possess capabilities comparable to humans in handling reasoning tasks remains unclear at present. In this paper, we propose Human-Aligned Bench, a benchmark for fine-grained alignment of multimodal reasoning with hum","authors_text":"Kaipeng Zhang, Li Xiao, Pengfei Zhou, Yansheng Qiu, Zhaopan Xu, Zheng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T11:41:19Z","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11141","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":"sha256:3dc2ea4c0e822a6993c330cdc081266f1a76016aec215aed1e07468d0e1a40aa","target":"record","created_at":"2026-07-05T11:08:41Z","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":"eee371575000dce57e80b68203a00ce5765a1a0d374b49c863543044a188708c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T11:41:19Z","title_canon_sha256":"cbe52123a492e087d8a8947eacd9cd8a857a5d662dc26fae0ec24390a235eaf8"},"schema_version":"1.0","source":{"id":"2505.11141","kind":"arxiv","version":2}},"canonical_sha256":"aaefef177e237b2529467a7b58eae6a8590af2c157d735e453cc1cfba01eb14c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaefef177e237b2529467a7b58eae6a8590af2c157d735e453cc1cfba01eb14c","first_computed_at":"2026-07-05T11:08:41.256988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:41.256988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YonJ7ro5QXKARW9KLKPLNqZZ5OFRTw04JL8Nr831l+yctDydZRju9kJjHq+IYQIRjXzkLcaemO5VoeHL9P46CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:41.257418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc2ea4c0e822a6993c330cdc081266f1a76016aec215aed1e07468d0e1a40aa","sha256:6b76199a9cb744c524edd4deb504f2b4935d759984fd220495096195e880c853"],"state_sha256":"fb1d3bc161e1f6992233f2de9068cb0b2515d191c0fd0f4ffdc670504b45b501"}