{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JXQ5SNKBJGTGS2KWGAVEFXAPA","short_pith_number":"pith:3JXQ5SNK","schema_version":"1.0","canonical_sha256":"da6f0ec9aa0a4d334b4ab1815216e078330213d3e9c81cdcf469e32ecc6b473b","source":{"kind":"arxiv","id":"2404.19063","version":1},"attestation_state":"computed","paper":{"title":"SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Xue, Lei Zhu, Liang Xu, Yaotong Wu","submitted_at":"2024-04-29T19:04:35Z","abstract_excerpt":"The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs). It assesses FLMs across six financial application domains and twenty-five specialized tasks, encompassing theoretical knowledge and practical applications such as compliance, risk management, and investment analysis. Using multi-turn, open-ended conversations that mimic real-life scenarios, SC-Fin measures models on a range of criteria, including accurate financial understanding, logical reasoning, clarity, computational efficiency, business acumen, risk"},"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":"2404.19063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T19:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"dac9f1d5e0a10c657b94ee6e14da74741f3b7e54a4d3f2beda6ab2adfe796c40","abstract_canon_sha256":"5996a0e56d46b353d877f866571f3f432e5f4a3bd8e99302e9ae2c59515b2fd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:37.104172Z","signature_b64":"JgBtj68fGB2556Pjd7sONRBeag2MAzQZTdHinep+b468l/mhO/vNB6bNDdhzSdkOHgYzMw6lz4Jo4w76kotPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da6f0ec9aa0a4d334b4ab1815216e078330213d3e9c81cdcf469e32ecc6b473b","last_reissued_at":"2026-07-05T08:13:37.103669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:37.103669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Xue, Lei Zhu, Liang Xu, Yaotong Wu","submitted_at":"2024-04-29T19:04:35Z","abstract_excerpt":"The SuperCLUE-Fin (SC-Fin) benchmark is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs). It assesses FLMs across six financial application domains and twenty-five specialized tasks, encompassing theoretical knowledge and practical applications such as compliance, risk management, and investment analysis. Using multi-turn, open-ended conversations that mimic real-life scenarios, SC-Fin measures models on a range of criteria, including accurate financial understanding, logical reasoning, clarity, computational efficiency, business acumen, risk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19063","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/2404.19063/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":"2404.19063","created_at":"2026-07-05T08:13:37.103735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19063v1","created_at":"2026-07-05T08:13:37.103735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19063","created_at":"2026-07-05T08:13:37.103735+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JXQ5SNKBJGT","created_at":"2026-07-05T08:13:37.103735+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JXQ5SNKBJGTGS2K","created_at":"2026-07-05T08:13:37.103735+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JXQ5SNK","created_at":"2026-07-05T08:13:37.103735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.17011","citing_title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17962","citing_title":"FinDocMRE: A Benchmark for Document-Level Financial Multimodal Reasoning Evaluation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15367","citing_title":"SoK: Security of Autonomous LLM Agents in Agentic Commerce","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17305","citing_title":"BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA","json":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA.json","graph_json":"https://pith.science/api/pith-number/3JXQ5SNKBJGTGS2KWGAVEFXAPA/graph.json","events_json":"https://pith.science/api/pith-number/3JXQ5SNKBJGTGS2KWGAVEFXAPA/events.json","paper":"https://pith.science/paper/3JXQ5SNK"},"agent_actions":{"view_html":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA","download_json":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA.json","view_paper":"https://pith.science/paper/3JXQ5SNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19063&json=true","fetch_graph":"https://pith.science/api/pith-number/3JXQ5SNKBJGTGS2KWGAVEFXAPA/graph.json","fetch_events":"https://pith.science/api/pith-number/3JXQ5SNKBJGTGS2KWGAVEFXAPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA/action/storage_attestation","attest_author":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA/action/author_attestation","sign_citation":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA/action/citation_signature","submit_replication":"https://pith.science/pith/3JXQ5SNKBJGTGS2KWGAVEFXAPA/action/replication_record"}},"created_at":"2026-07-05T08:13:37.103735+00:00","updated_at":"2026-07-05T08:13:37.103735+00:00"}