{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YXOBVXWFP6J2JRSUTDYFDOAQQL","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":"4479235ef49415303d5f499cbd48c21b7e1a9208f920061b8b1bb22769cd8897","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T12:12:27Z","title_canon_sha256":"dcccf2f19c40ef6789741008361c2a196134232790b24e011966c70f5d651691"},"schema_version":"1.0","source":{"id":"2605.29833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29833","created_at":"2026-05-29T02:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29833v1","created_at":"2026-05-29T02:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29833","created_at":"2026-05-29T02:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"YXOBVXWFP6J2","created_at":"2026-05-29T02:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"YXOBVXWFP6J2JRSU","created_at":"2026-05-29T02:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"YXOBVXWF","created_at":"2026-05-29T02:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:49f62461098447f6b6ec6e6ec6585a3b665fd4a64f46f299028985658e87d7ef","target":"graph","created_at":"2026-05-29T02:05:55Z","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/2605.29833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multimodal language models play an increasingly important role in scientific research, materials science offers a critical testbed due to its interdisciplinary, multimodal, and application-driven nature. However, existing materials benchmarks mainly focus on property prediction, knowledge QA, or characterization understanding, leaving the broader reasoning process from materials knowledge to application underexplored. To fill this gap, we present OmniMatBench, a human-calibrated multimodal reasoning benchmark for materials science. OmniMatBench contains 3,171 expert-curated QA and calculati","authors_text":"Jiaqing Xie, Jue Wang, Lei Bai, Lu Chen, Qian Tan, Ran Sun, Tianfan Fu, Wanhao Liu, Wanli Ouyang, Weida Wang, Xin Chen, Yuqiang Li, Zhuo Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T12:12:27Z","title":"OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29833","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":"sha256:0f8630695aba383dc1ca5d1a1467028080854812d94182427b78f12164f8e75d","target":"record","created_at":"2026-05-29T02:05:55Z","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":"4479235ef49415303d5f499cbd48c21b7e1a9208f920061b8b1bb22769cd8897","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T12:12:27Z","title_canon_sha256":"dcccf2f19c40ef6789741008361c2a196134232790b24e011966c70f5d651691"},"schema_version":"1.0","source":{"id":"2605.29833","kind":"arxiv","version":1}},"canonical_sha256":"c5dc1adec57f93a4c65498f051b81082fcdc05dc42efca473be43eb159ad56d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5dc1adec57f93a4c65498f051b81082fcdc05dc42efca473be43eb159ad56d6","first_computed_at":"2026-05-29T02:05:55.248705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:55.248705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwYyxbjrdc7ZP+KUSeMmGqKRZWymZKtmnAnIwEm4Q1AFyBK8HOPHbd8Iw46BNGw/+1DE7YerucpF97lmgWscBw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:55.249459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f8630695aba383dc1ca5d1a1467028080854812d94182427b78f12164f8e75d","sha256:49f62461098447f6b6ec6e6ec6585a3b665fd4a64f46f299028985658e87d7ef"],"state_sha256":"8a16a3eb316545a47bab481d575ab8b704633bbbbe2221e012b50c3c336be98d"}