{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FTAXDLOWHZBB3GJCGY63FVBLRS","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":"2092757901d7fe35f83ba6c89c43590bf0efb3c59eb859a575149aaa7e0bb33e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:55:52Z","title_canon_sha256":"45ee57ab91e8b62e29ad475b90b30acedfbec966e5be7e8f147853ccddb3f5b7"},"schema_version":"1.0","source":{"id":"2501.05444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05444","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05444v1","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05444","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"FTAXDLOWHZBB","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"FTAXDLOWHZBB3GJC","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"FTAXDLOW","created_at":"2026-07-05T09:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:9ab29af217864c535f1520c6cc52d628ca8aabd270ad703e17a0fa5975356fa3","target":"graph","created_at":"2026-07-05T09:59:10Z","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/2501.05444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such multimodal reasoning remains under-explored. Existing benchmarks often emphasize text-dominant reasoning or rely on shallow visual cues, failing to adequately assess integrated visual and textual reasoning. We introduce EMMA (Enhanced MultiModal reAsoning), a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding. EMMA tasks demand advanced cross-modal reasoning that canno","authors_text":"Huichen Will Wang, Jiawei Gu, Lijuan Wang, Linjie Li, Yu Cheng, Yunzhuo Hao, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:55:52Z","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05444","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":"sha256:7e7ea67b6aae0b587caf09fc7206fd82a058c70f1e988342b575fe4975daf06a","target":"record","created_at":"2026-07-05T09:59:10Z","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":"2092757901d7fe35f83ba6c89c43590bf0efb3c59eb859a575149aaa7e0bb33e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:55:52Z","title_canon_sha256":"45ee57ab91e8b62e29ad475b90b30acedfbec966e5be7e8f147853ccddb3f5b7"},"schema_version":"1.0","source":{"id":"2501.05444","kind":"arxiv","version":1}},"canonical_sha256":"2cc171add63e421d9922363db2d42b8caf0a5ee7428a66ca76fff0cf9f007099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cc171add63e421d9922363db2d42b8caf0a5ee7428a66ca76fff0cf9f007099","first_computed_at":"2026-07-05T09:59:10.004174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:10.004174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nOocXfHyBw9ADms++gqdKWRCbyv/pm6RiNlVDpzoIgscmq94X6PaqTkFypqe1B4JAW3nPAevSHlAcViiV2ZbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:10.004621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e7ea67b6aae0b587caf09fc7206fd82a058c70f1e988342b575fe4975daf06a","sha256:9ab29af217864c535f1520c6cc52d628ca8aabd270ad703e17a0fa5975356fa3"],"state_sha256":"de89b002d6a7dfb0cb1470ac3f6f9c5944f6b97047f5dae9173f387e23f49797"}