{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GWO5ISPBVV74BUZQG4G4QMSDDB","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":"395a832b938be30d34599e928327a96bff82d1804d7aa3ef9d9c5c972a3b6843","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T01:34:25Z","title_canon_sha256":"012b7b88f3e5008dce3e77d75229bc628f4192cafa54f8a349b5365faa4dc736"},"schema_version":"1.0","source":{"id":"2505.24120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24120","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24120v2","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24120","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"GWO5ISPBVV74","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"GWO5ISPBVV74BUZQ","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"GWO5ISPB","created_at":"2026-07-05T11:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:2c8c6bf39ffdb4faada35bccb1ef4ffca392ad880ed7fae5326e30caa9fe8770","target":"graph","created_at":"2026-07-05T11:22:41Z","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/2505.24120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal understanding, yet their capabilities for scientific reasoning remain inadequately assessed. Current multimodal benchmarks predominantly evaluate generic image comprehension or text-driven reasoning, lacking authentic scientific contexts that require domain-specific knowledge integration with visual evidence analysis. To fill this gap, we present CSVQA, a diagnostic multimodal benchmark specifically designed for evaluating scientific reasoning through domain-grounded visual question answering. Our benchmark featu","authors_text":"Ai Jian, Jiangbo Pei, Peiyu Wang, Weijie Qiu, Xiaokun Wang, Xuchen Song, Yichen Wei, Yi Peng, Yunzhuo Hao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T01:34:25Z","title":"CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24120","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":"sha256:372f5bf90728766202e05fa4a9bd829c099220130e55ccdc727e8872130f12ef","target":"record","created_at":"2026-07-05T11:22:41Z","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":"395a832b938be30d34599e928327a96bff82d1804d7aa3ef9d9c5c972a3b6843","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T01:34:25Z","title_canon_sha256":"012b7b88f3e5008dce3e77d75229bc628f4192cafa54f8a349b5365faa4dc736"},"schema_version":"1.0","source":{"id":"2505.24120","kind":"arxiv","version":2}},"canonical_sha256":"359dd449e1ad7fc0d330370dc83243187b99ccc680d9145c75dabd58aba7676e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"359dd449e1ad7fc0d330370dc83243187b99ccc680d9145c75dabd58aba7676e","first_computed_at":"2026-07-05T11:22:41.068946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:41.068946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0uMtl7jNJQ2pXEQx1kW+ct1BlwpwgQoiXIdBISBtLkNqmM83DkhKnaaNwGEt3Tuo1XcnNT+2Dfzrt4+tgBOqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:41.069460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:372f5bf90728766202e05fa4a9bd829c099220130e55ccdc727e8872130f12ef","sha256:2c8c6bf39ffdb4faada35bccb1ef4ffca392ad880ed7fae5326e30caa9fe8770"],"state_sha256":"72203a89103374d29e8a786efa38255b1a1eb7a72baa190135b68daf54b9fc4b"}