{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W5DPYLKNS3AUR4WBXYWSG7JB3N","short_pith_number":"pith:W5DPYLKN","schema_version":"1.0","canonical_sha256":"b746fc2d4d96c148f2c1be2d237d21db6e428adc1873ea29f4322a4d7f02c72a","source":{"kind":"arxiv","id":"2603.19225","version":3},"attestation_state":"computed","paper":{"title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","q-fin.CP"],"primary_cat":"cs.CE","authors_text":"Aniruddha Dutta, Aritra Dutta, Md Mahadi Hasan, Santu Karmaker, Yogesh Agrawal","submitted_at":"2026-03-19T17:59:41Z","abstract_excerpt":"Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with advances in Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question-answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning about how company stocks trade in the market or their interactions with fundam"},"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":"2603.19225","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2026-03-19T17:59:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","q-fin.CP"],"title_canon_sha256":"52d29d949b4352fb8c4a79f92cab82e8d4185c6eb46f4b3eebe9118c383ed56a","abstract_canon_sha256":"43d8b9fb0c49fb26a43ccaafe18616a2fb7c2f6daf6dccbeac2f95041abfc819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:48.746991Z","signature_b64":"nZEHwCBQ6w2yrnxCEYGLvQAdJQXMzKFUGJeEiF/42KKP+BKwZGV4E+i9mljWTdJDosG06+G6WYp6lOQvwdSACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b746fc2d4d96c148f2c1be2d237d21db6e428adc1873ea29f4322a4d7f02c72a","last_reissued_at":"2026-06-04T01:08:48.746007Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:48.746007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","q-fin.CP"],"primary_cat":"cs.CE","authors_text":"Aniruddha Dutta, Aritra Dutta, Md Mahadi Hasan, Santu Karmaker, Yogesh Agrawal","submitted_at":"2026-03-19T17:59:41Z","abstract_excerpt":"Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with advances in Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question-answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning about how company stocks trade in the market or their interactions with fundam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19225","kind":"arxiv","version":3},"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/2603.19225/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":"2603.19225","created_at":"2026-06-04T01:08:48.746260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.19225v3","created_at":"2026-06-04T01:08:48.746260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19225","created_at":"2026-06-04T01:08:48.746260+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5DPYLKNS3AU","created_at":"2026-06-04T01:08:48.746260+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5DPYLKNS3AUR4WB","created_at":"2026-06-04T01:08:48.746260+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5DPYLKN","created_at":"2026-06-04T01:08:48.746260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.09185","citing_title":"AutoRedTrader: Autonomous Red Teaming of Trading Agents through Synthetic Misinformation Injection","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18576","citing_title":"Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N","json":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N.json","graph_json":"https://pith.science/api/pith-number/W5DPYLKNS3AUR4WBXYWSG7JB3N/graph.json","events_json":"https://pith.science/api/pith-number/W5DPYLKNS3AUR4WBXYWSG7JB3N/events.json","paper":"https://pith.science/paper/W5DPYLKN"},"agent_actions":{"view_html":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N","download_json":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N.json","view_paper":"https://pith.science/paper/W5DPYLKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.19225&json=true","fetch_graph":"https://pith.science/api/pith-number/W5DPYLKNS3AUR4WBXYWSG7JB3N/graph.json","fetch_events":"https://pith.science/api/pith-number/W5DPYLKNS3AUR4WBXYWSG7JB3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N/action/storage_attestation","attest_author":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N/action/author_attestation","sign_citation":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N/action/citation_signature","submit_replication":"https://pith.science/pith/W5DPYLKNS3AUR4WBXYWSG7JB3N/action/replication_record"}},"created_at":"2026-06-04T01:08:48.746260+00:00","updated_at":"2026-06-04T01:08:48.746260+00:00"}