{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VUJUEF566W4EPAS47OHQ3FI7G","short_pith_number":"pith:2VUJUEF5","schema_version":"1.0","canonical_sha256":"d5689a10bdf7adc23c12e7dc786ca8f99e8229b40eee10f8b24d1d3461355393","source":{"kind":"arxiv","id":"2410.04526","version":4},"attestation_state":"computed","paper":{"title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Zhou, Hongyuan Mei, Qingyang Dai, Siqiao Xue, Xiaojing Li, Zhixuan Chu","submitted_at":"2024-10-06T15:41:26Z","abstract_excerpt":"In this paper, we introduce FAMMA, an open-source benchmark for \\underline{f}in\\underline{a}ncial \\underline{m}ultilingual \\underline{m}ultimodal question \\underline{a}nswering (QA). Our benchmark aims to evaluate the abilities of large language models (LLMs) in answering complex reasoning questions that require advanced financial knowledge. The benchmark has two versions: FAMMA-Basic consists of 1,945 questions extracted from university textbooks and exams, along with human-annotated answers and rationales; FAMMA-LivePro consists of 103 novel questions created by human domain experts, with an"},"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":"2410.04526","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T15:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c94227e2e3c4d79568bf91684ac42116dcf0f27401fc940547d7743299f9610","abstract_canon_sha256":"78294e70b945a91922c3b8f2728293cd016ce0bba11a7f2983947205b5c8fe15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:17.151517Z","signature_b64":"zHteMoLSDnOhUkOBXlmK5MViMwmOQe4zh74VDrMxkMQkHcGiK9TjiLtexxGNOto01ne+mA72CEOfLD6lvnXVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5689a10bdf7adc23c12e7dc786ca8f99e8229b40eee10f8b24d1d3461355393","last_reissued_at":"2026-07-05T11:03:17.151070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:17.151070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Zhou, Hongyuan Mei, Qingyang Dai, Siqiao Xue, Xiaojing Li, Zhixuan Chu","submitted_at":"2024-10-06T15:41:26Z","abstract_excerpt":"In this paper, we introduce FAMMA, an open-source benchmark for \\underline{f}in\\underline{a}ncial \\underline{m}ultilingual \\underline{m}ultimodal question \\underline{a}nswering (QA). Our benchmark aims to evaluate the abilities of large language models (LLMs) in answering complex reasoning questions that require advanced financial knowledge. The benchmark has two versions: FAMMA-Basic consists of 1,945 questions extracted from university textbooks and exams, along with human-annotated answers and rationales; FAMMA-LivePro consists of 103 novel questions created by human domain experts, with an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04526","kind":"arxiv","version":4},"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/2410.04526/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":"2410.04526","created_at":"2026-07-05T11:03:17.151124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04526v4","created_at":"2026-07-05T11:03:17.151124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04526","created_at":"2026-07-05T11:03:17.151124+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VUJUEF566W4","created_at":"2026-07-05T11:03:17.151124+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VUJUEF566W4EPAS","created_at":"2026-07-05T11:03:17.151124+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VUJUEF5","created_at":"2026-07-05T11:03:17.151124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03829","citing_title":"BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31073","citing_title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27708","citing_title":"ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30049","citing_title":"Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17962","citing_title":"FinDocMRE: A Benchmark for Document-Level Financial Multimodal Reasoning Evaluation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08339","citing_title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G","json":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G.json","graph_json":"https://pith.science/api/pith-number/2VUJUEF566W4EPAS47OHQ3FI7G/graph.json","events_json":"https://pith.science/api/pith-number/2VUJUEF566W4EPAS47OHQ3FI7G/events.json","paper":"https://pith.science/paper/2VUJUEF5"},"agent_actions":{"view_html":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G","download_json":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G.json","view_paper":"https://pith.science/paper/2VUJUEF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04526&json=true","fetch_graph":"https://pith.science/api/pith-number/2VUJUEF566W4EPAS47OHQ3FI7G/graph.json","fetch_events":"https://pith.science/api/pith-number/2VUJUEF566W4EPAS47OHQ3FI7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G/action/storage_attestation","attest_author":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G/action/author_attestation","sign_citation":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G/action/citation_signature","submit_replication":"https://pith.science/pith/2VUJUEF566W4EPAS47OHQ3FI7G/action/replication_record"}},"created_at":"2026-07-05T11:03:17.151124+00:00","updated_at":"2026-07-05T11:03:17.151124+00:00"}