{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KYVVAXVM6YCZ45EPAAPTSUMMGO","short_pith_number":"pith:KYVVAXVM","schema_version":"1.0","canonical_sha256":"562b505eacf6059e748f001f39518c33ab9908286452dad75128d10295d8c58d","source":{"kind":"arxiv","id":"2607.28661","version":1},"attestation_state":"computed","paper":{"title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"An Yang, Bing Zhao, Boyu Yang, Dayiheng Liu, Guojie Lin, Hu Wei, Jiatu Hu, Lingfeng Zeng, Lin Qu, Tianyi Tang, Xinke Tong, Xuanming Zhang, Zhenzhen Shi","submitted_at":"2026-07-22T06:53:07Z","abstract_excerpt":"Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture real-world industrial complexity, predominantly relying on multiple-choice questions or single-hop QA over cropped tables while ignoring intricate cross-statement dynamics and temporal de-cumulation.\n  To bridge this gap, we introduce FinIndices, a large-scale benchmark evaluating data-processing fidelity over uncropped financia"},"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":"2607.28661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T06:53:07Z","cross_cats_sorted":[],"title_canon_sha256":"b94e04a08a50b8884c9a4bcfd0ffd89e1d6b9bb361c49626c3f2fb809b890355","abstract_canon_sha256":"dc77f0cb60ac8f0b2e893dd0a8fde346bb19330b885e0c5c5d25dc427664b321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:12:00.864919Z","signature_b64":"g4uq5v2Q6oLqWOJXAYImMH3xY2vhvWmpEPDAUAwNNHfBjWgHziwl6ht2EGDMrz/DIEURkLNWqV0MSSihJxlFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"562b505eacf6059e748f001f39518c33ab9908286452dad75128d10295d8c58d","last_reissued_at":"2026-08-03T00:12:00.861969Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:12:00.861969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"An Yang, Bing Zhao, Boyu Yang, Dayiheng Liu, Guojie Lin, Hu Wei, Jiatu Hu, Lingfeng Zeng, Lin Qu, Tianyi Tang, Xinke Tong, Xuanming Zhang, Zhenzhen Shi","submitted_at":"2026-07-22T06:53:07Z","abstract_excerpt":"Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture real-world industrial complexity, predominantly relying on multiple-choice questions or single-hop QA over cropped tables while ignoring intricate cross-statement dynamics and temporal de-cumulation.\n  To bridge this gap, we introduce FinIndices, a large-scale benchmark evaluating data-processing fidelity over uncropped financia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28661","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/2607.28661/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":"2607.28661","created_at":"2026-08-03T00:12:00.863474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28661v1","created_at":"2026-08-03T00:12:00.863474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28661","created_at":"2026-08-03T00:12:00.863474+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYVVAXVM6YCZ","created_at":"2026-08-03T00:12:00.863474+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYVVAXVM6YCZ45EP","created_at":"2026-08-03T00:12:00.863474+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYVVAXVM","created_at":"2026-08-03T00:12:00.863474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO","json":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO.json","graph_json":"https://pith.science/api/pith-number/KYVVAXVM6YCZ45EPAAPTSUMMGO/graph.json","events_json":"https://pith.science/api/pith-number/KYVVAXVM6YCZ45EPAAPTSUMMGO/events.json","paper":"https://pith.science/paper/KYVVAXVM"},"agent_actions":{"view_html":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO","download_json":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO.json","view_paper":"https://pith.science/paper/KYVVAXVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28661&json=true","fetch_graph":"https://pith.science/api/pith-number/KYVVAXVM6YCZ45EPAAPTSUMMGO/graph.json","fetch_events":"https://pith.science/api/pith-number/KYVVAXVM6YCZ45EPAAPTSUMMGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO/action/storage_attestation","attest_author":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO/action/author_attestation","sign_citation":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO/action/citation_signature","submit_replication":"https://pith.science/pith/KYVVAXVM6YCZ45EPAAPTSUMMGO/action/replication_record"}},"created_at":"2026-08-03T00:12:00.863474+00:00","updated_at":"2026-08-03T00:12:00.863474+00:00"}