{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OQFOSNPSTA7XQKG3H6EDIRLJIC","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":"65a6ea455584f1b90412107cc26fe4089660db8959a868c9872787e2afa54b4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T15:38:43Z","title_canon_sha256":"f1b9ef122b5f641438384e389f7ae737dabc5d9abb3dc12e7acd4a9105b1e438"},"schema_version":"1.0","source":{"id":"2503.01891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01891","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01891v2","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01891","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"OQFOSNPSTA7X","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"OQFOSNPSTA7XQKG3","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"OQFOSNPS","created_at":"2026-07-05T11:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:4aaea85f5aded70fac598d2d5362ec7b8216aef0dbb0648b4ceaa1689160c711","target":"graph","created_at":"2026-07-05T11:13:21Z","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/2503.01891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings. We present MMSciBench, a benchmark for evaluating mathematical and physical reasoning through text-only and text-image formats, with human-annotated difficulty levels, solutions with detailed explanations, and taxonomic mappings. Evaluation of state-of-the-art models reveals significant limitations, with even the best model achieving only \\textbf{63.77\\%} accuracy and particular","authors_text":"Chengfan Li, Siming Chen, Wei Wei, Xiangru Tang, Xinwu Ye","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T15:38:43Z","title":"MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01891","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":"sha256:8f09238e7ee956f34eae109326a916daab327211c143293b509b0aabeb961b34","target":"record","created_at":"2026-07-05T11:13:21Z","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":"65a6ea455584f1b90412107cc26fe4089660db8959a868c9872787e2afa54b4a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T15:38:43Z","title_canon_sha256":"f1b9ef122b5f641438384e389f7ae737dabc5d9abb3dc12e7acd4a9105b1e438"},"schema_version":"1.0","source":{"id":"2503.01891","kind":"arxiv","version":2}},"canonical_sha256":"740ae935f2983f7828db3f8834456940b1244c3bacbe98cbc871107384d3d362","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"740ae935f2983f7828db3f8834456940b1244c3bacbe98cbc871107384d3d362","first_computed_at":"2026-07-05T11:13:21.963797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:21.963797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"27lIDEUlX5YDCidfp6VrDLMZgim5KNN+pL26Q5TAneYE7Byxw2dKsEPH8XX+PrtUtsYBxBz2zVHgvoZNeKj6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:21.964232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f09238e7ee956f34eae109326a916daab327211c143293b509b0aabeb961b34","sha256:4aaea85f5aded70fac598d2d5362ec7b8216aef0dbb0648b4ceaa1689160c711"],"state_sha256":"1eb99a332082d73fb5e0aa3e146381c7275ff54b4400c5a5d509fbdabcd8cb82"}