{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AJCSE3NBCHCCQM53BLWM7HPSK6","short_pith_number":"pith:AJCSE3NB","schema_version":"1.0","canonical_sha256":"0245226da111c42833bb0aeccf9df257bf52816ca5c8e0ffd5e4679600a3a278","source":{"kind":"arxiv","id":"2504.15716","version":1},"attestation_state":"computed","paper":{"title":"DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chi Zhang, Feng Chen, Huaixia Dou, Jie Zhu, Junhui Li, Lifan Guo, Qian Chen","submitted_at":"2025-04-22T09:01:04Z","abstract_excerpt":"Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenar"},"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":"2504.15716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T09:01:04Z","cross_cats_sorted":[],"title_canon_sha256":"5c0dc294502cf4bd774dd368ef1933afb7ce438124f010d47cc7305c571ecdc4","abstract_canon_sha256":"a6688cbdcff817eb448304756dd2b491b1984133e7f1edee24fc9d81b50d71e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:28.735544Z","signature_b64":"MgEn9YYRmOI5CpkCP6bXTZtfLxjSmVsPkSbdqqVWjIYP/IgsuDKrCiMdEYLetlAL20dvOuNNyWa9z6uWnO18BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0245226da111c42833bb0aeccf9df257bf52816ca5c8e0ffd5e4679600a3a278","last_reissued_at":"2026-07-05T10:52:28.735015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:28.735015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chi Zhang, Feng Chen, Huaixia Dou, Jie Zhu, Junhui Li, Lifan Guo, Qian Chen","submitted_at":"2025-04-22T09:01:04Z","abstract_excerpt":"Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose DianJin-R1, a reasoning-enhanced framework designed to address these challenges through reasoning-augmented supervision and reinforcement learning. Central to our approach is DianJin-R1-Data, a high-quality dataset constructed from CFLUE, FinQA, and a proprietary compliance corpus (Chinese Compliance Check, CCC), combining diverse financial reasoning scenar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15716","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/2504.15716/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":"2504.15716","created_at":"2026-07-05T10:52:28.735092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15716v1","created_at":"2026-07-05T10:52:28.735092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15716","created_at":"2026-07-05T10:52:28.735092+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJCSE3NBCHCC","created_at":"2026-07-05T10:52:28.735092+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJCSE3NBCHCCQM53","created_at":"2026-07-05T10:52:28.735092+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJCSE3NB","created_at":"2026-07-05T10:52:28.735092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24901","citing_title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05868","citing_title":"YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21975","citing_title":"Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15202","citing_title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19254","citing_title":"FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12160","citing_title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02557","citing_title":"VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6","json":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6.json","graph_json":"https://pith.science/api/pith-number/AJCSE3NBCHCCQM53BLWM7HPSK6/graph.json","events_json":"https://pith.science/api/pith-number/AJCSE3NBCHCCQM53BLWM7HPSK6/events.json","paper":"https://pith.science/paper/AJCSE3NB"},"agent_actions":{"view_html":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6","download_json":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6.json","view_paper":"https://pith.science/paper/AJCSE3NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15716&json=true","fetch_graph":"https://pith.science/api/pith-number/AJCSE3NBCHCCQM53BLWM7HPSK6/graph.json","fetch_events":"https://pith.science/api/pith-number/AJCSE3NBCHCCQM53BLWM7HPSK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6/action/storage_attestation","attest_author":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6/action/author_attestation","sign_citation":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6/action/citation_signature","submit_replication":"https://pith.science/pith/AJCSE3NBCHCCQM53BLWM7HPSK6/action/replication_record"}},"created_at":"2026-07-05T10:52:28.735092+00:00","updated_at":"2026-07-05T10:52:28.735092+00:00"}