{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PXCU7MIBJ6Y6E4SED4VC7WTS27","short_pith_number":"pith:PXCU7MIB","schema_version":"1.0","canonical_sha256":"7dc54fb1014fb1e272441f2a2fda72d7fb10ee454011e73c89ae569c1c054180","source":{"kind":"arxiv","id":"2605.29462","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Feng Chen, Lifan Guo, Qian Chen, Xianyin Zhang, Yanzhi Liu","submitted_at":"2026-05-28T06:56:33Z","abstract_excerpt":"The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified inference across both visual and textual modalities and supporting a broader range of real-world applications. To comprehensively evaluate the perception, understanding, reasoning, and cognition capabilities of LVLMs throughout the entire financial business workflow in Chinese contexts, we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark. CFMME comprises 6,052 instances spanning from fundamental academic knowledge to comp"},"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":"2605.29462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T06:56:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b07939c3955de4a3964f8b401d750fa4e9926ab019c7d80353ce589c0cc7d625","abstract_canon_sha256":"a74427c742216009ee8620647f70ba1a0dae80642c787794dbb7732d50cb6544"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:40.871009Z","signature_b64":"WDkgffIl+1Bp8X6odxHfhimH7KDRdnn2qzSgyQYnMP5aeJKK28yH/JaxgsdvCErg8F5bPzFWu+2OTUMH7DatAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc54fb1014fb1e272441f2a2fda72d7fb10ee454011e73c89ae569c1c054180","last_reissued_at":"2026-05-29T01:05:40.870207Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:40.870207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Feng Chen, Lifan Guo, Qian Chen, Xianyin Zhang, Yanzhi Liu","submitted_at":"2026-05-28T06:56:33Z","abstract_excerpt":"The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified inference across both visual and textual modalities and supporting a broader range of real-world applications. To comprehensively evaluate the perception, understanding, reasoning, and cognition capabilities of LVLMs throughout the entire financial business workflow in Chinese contexts, we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark. CFMME comprises 6,052 instances spanning from fundamental academic knowledge to comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29462","kind":"arxiv","version":1},"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/2605.29462/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":"2605.29462","created_at":"2026-05-29T01:05:40.870330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29462v1","created_at":"2026-05-29T01:05:40.870330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29462","created_at":"2026-05-29T01:05:40.870330+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXCU7MIBJ6Y6","created_at":"2026-05-29T01:05:40.870330+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXCU7MIBJ6Y6E4SE","created_at":"2026-05-29T01:05:40.870330+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXCU7MIB","created_at":"2026-05-29T01:05:40.870330+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27","json":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27.json","graph_json":"https://pith.science/api/pith-number/PXCU7MIBJ6Y6E4SED4VC7WTS27/graph.json","events_json":"https://pith.science/api/pith-number/PXCU7MIBJ6Y6E4SED4VC7WTS27/events.json","paper":"https://pith.science/paper/PXCU7MIB"},"agent_actions":{"view_html":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27","download_json":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27.json","view_paper":"https://pith.science/paper/PXCU7MIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29462&json=true","fetch_graph":"https://pith.science/api/pith-number/PXCU7MIBJ6Y6E4SED4VC7WTS27/graph.json","fetch_events":"https://pith.science/api/pith-number/PXCU7MIBJ6Y6E4SED4VC7WTS27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27/action/storage_attestation","attest_author":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27/action/author_attestation","sign_citation":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27/action/citation_signature","submit_replication":"https://pith.science/pith/PXCU7MIBJ6Y6E4SED4VC7WTS27/action/replication_record"}},"created_at":"2026-05-29T01:05:40.870330+00:00","updated_at":"2026-05-29T01:05:40.870330+00:00"}