{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GWO5ISPBVV74BUZQG4G4QMSDDB","short_pith_number":"pith:GWO5ISPB","schema_version":"1.0","canonical_sha256":"359dd449e1ad7fc0d330370dc83243187b99ccc680d9145c75dabd58aba7676e","source":{"kind":"arxiv","id":"2505.24120","version":2},"attestation_state":"computed","paper":{"title":"CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ai Jian, Jiangbo Pei, Peiyu Wang, Weijie Qiu, Xiaokun Wang, Xuchen Song, Yichen Wei, Yi Peng, Yunzhuo Hao","submitted_at":"2025-05-30T01:34:25Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.24120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T01:34:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"012b7b88f3e5008dce3e77d75229bc628f4192cafa54f8a349b5365faa4dc736","abstract_canon_sha256":"395a832b938be30d34599e928327a96bff82d1804d7aa3ef9d9c5c972a3b6843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:41.069460Z","signature_b64":"0uMtl7jNJQ2pXEQx1kW+ct1BlwpwgQoiXIdBISBtLkNqmM83DkhKnaaNwGEt3Tuo1XcnNT+2Dfzrt4+tgBOqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"359dd449e1ad7fc0d330370dc83243187b99ccc680d9145c75dabd58aba7676e","last_reissued_at":"2026-07-05T11:22:41.068946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:41.068946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ai Jian, Jiangbo Pei, Peiyu Wang, Weijie Qiu, Xiaokun Wang, Xuchen Song, Yichen Wei, Yi Peng, Yunzhuo Hao","submitted_at":"2025-05-30T01:34:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24120","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.24120/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.24120","created_at":"2026-07-05T11:22:41.069006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24120v2","created_at":"2026-07-05T11:22:41.069006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24120","created_at":"2026-07-05T11:22:41.069006+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWO5ISPBVV74","created_at":"2026-07-05T11:22:41.069006+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWO5ISPBVV74BUZQ","created_at":"2026-07-05T11:22:41.069006+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWO5ISPB","created_at":"2026-07-05T11:22:41.069006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02378","citing_title":"Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB","json":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB.json","graph_json":"https://pith.science/api/pith-number/GWO5ISPBVV74BUZQG4G4QMSDDB/graph.json","events_json":"https://pith.science/api/pith-number/GWO5ISPBVV74BUZQG4G4QMSDDB/events.json","paper":"https://pith.science/paper/GWO5ISPB"},"agent_actions":{"view_html":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB","download_json":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB.json","view_paper":"https://pith.science/paper/GWO5ISPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24120&json=true","fetch_graph":"https://pith.science/api/pith-number/GWO5ISPBVV74BUZQG4G4QMSDDB/graph.json","fetch_events":"https://pith.science/api/pith-number/GWO5ISPBVV74BUZQG4G4QMSDDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB/action/storage_attestation","attest_author":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB/action/author_attestation","sign_citation":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB/action/citation_signature","submit_replication":"https://pith.science/pith/GWO5ISPBVV74BUZQG4G4QMSDDB/action/replication_record"}},"created_at":"2026-07-05T11:22:41.069006+00:00","updated_at":"2026-07-05T11:22:41.069006+00:00"}