{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BKHNO3VPM5NDDTALM2KBDPBZO5","short_pith_number":"pith:BKHNO3VP","schema_version":"1.0","canonical_sha256":"0a8ed76eaf675a31cc0b669411bc397762c238a1872c29497bbbabbaf0dedb07","source":{"kind":"arxiv","id":"2505.24714","version":1},"attestation_state":"computed","paper":{"title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengzhong Liu, Jiaming Ji, Jingshu Peng, Jinsheng Huang, Junyu Luo, Liming Yang, Ming Zhang, Sirui Han, Xiao Luo, Xuanzhe Liu, Yike Guo, Zhiping Xiao, Zhizhuo Kou","submitted_at":"2025-05-30T15:36:19Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized multimodal evaluation datasets. To advance the development of MLLMs in the finance domain, we introduce FinMME, encompassing more than 11,000 high-quality financial research samples across 18 financial domains and 6 asset classes, featuring 10 major chart types and 21 subtypes. We ensure data quality through 20 annotators and carefully designed validation mechanisms. Additionally, we develop FinScore, an evaluation s"},"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":"2505.24714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:36:19Z","cross_cats_sorted":[],"title_canon_sha256":"e3aa143cb69ff9e76ab40b5a20d109083ed933581a9b73d7fc535fe4e3e7a133","abstract_canon_sha256":"784626cbcd88e62cb12262a12cf242facfbee5760eac95f3fddce132bf63faa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.321434Z","signature_b64":"cmi9YwIoYAYMVFUasslW7DXutWqcXpkfhvNd7eCtkZT4bK1XuFVuf8R3p6gVuUzUhrDogXB+vq5bCWGcQ7IaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a8ed76eaf675a31cc0b669411bc397762c238a1872c29497bbbabbaf0dedb07","last_reissued_at":"2026-07-05T11:12:55.320802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.320802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengzhong Liu, Jiaming Ji, Jingshu Peng, Jinsheng Huang, Junyu Luo, Liming Yang, Ming Zhang, Sirui Han, Xiao Luo, Xuanzhe Liu, Yike Guo, Zhiping Xiao, Zhizhuo Kou","submitted_at":"2025-05-30T15:36:19Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized multimodal evaluation datasets. To advance the development of MLLMs in the finance domain, we introduce FinMME, encompassing more than 11,000 high-quality financial research samples across 18 financial domains and 6 asset classes, featuring 10 major chart types and 21 subtypes. We ensure data quality through 20 annotators and carefully designed validation mechanisms. Additionally, we develop FinScore, an evaluation s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24714","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/2505.24714/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":"2505.24714","created_at":"2026-07-05T11:12:55.320887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24714v1","created_at":"2026-07-05T11:12:55.320887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24714","created_at":"2026-07-05T11:12:55.320887+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKHNO3VPM5ND","created_at":"2026-07-05T11:12:55.320887+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKHNO3VPM5NDDTAL","created_at":"2026-07-05T11:12:55.320887+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKHNO3VP","created_at":"2026-07-05T11:12:55.320887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17962","citing_title":"FinDocMRE: A Benchmark for Document-Level Financial Multimodal Reasoning Evaluation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14998","citing_title":"FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06024","citing_title":"Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5","json":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5.json","graph_json":"https://pith.science/api/pith-number/BKHNO3VPM5NDDTALM2KBDPBZO5/graph.json","events_json":"https://pith.science/api/pith-number/BKHNO3VPM5NDDTALM2KBDPBZO5/events.json","paper":"https://pith.science/paper/BKHNO3VP"},"agent_actions":{"view_html":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5","download_json":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5.json","view_paper":"https://pith.science/paper/BKHNO3VP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24714&json=true","fetch_graph":"https://pith.science/api/pith-number/BKHNO3VPM5NDDTALM2KBDPBZO5/graph.json","fetch_events":"https://pith.science/api/pith-number/BKHNO3VPM5NDDTALM2KBDPBZO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5/action/storage_attestation","attest_author":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5/action/author_attestation","sign_citation":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5/action/citation_signature","submit_replication":"https://pith.science/pith/BKHNO3VPM5NDDTALM2KBDPBZO5/action/replication_record"}},"created_at":"2026-07-05T11:12:55.320887+00:00","updated_at":"2026-07-05T11:12:55.320887+00:00"}