{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P6LO4ERZ2VZN65HPEMQSAWQCSR","short_pith_number":"pith:P6LO4ERZ","schema_version":"1.0","canonical_sha256":"7f96ee1239d572df74ef2321205a02946fdc5fb142ef1193f73eb293d26f4989","source":{"kind":"arxiv","id":"2608.04374","version":1},"attestation_state":"computed","paper":{"title":"FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jun Zhou, Tan Zhenwei, Wanli Gu, Wei Chen, Xiaolu Zhang, Yinghao Tang, Yiyao Wang","submitted_at":"2026-08-05T02:31:48Z","abstract_excerpt":"Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery. We introduce FinReportBench, an expert-grounded benchmark for measuring and improving institution-grade financial report generation. Expert review reveals recurring gaps in report identity, institutional components, source discipline, and visual delivery. We derive a 35-item rubric through expert partial orders, multimodal evidence, and audits of decision boundaries, covering deliverability, report identity, and institutional completeness. S"},"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":"2608.04374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T02:31:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ab9b49beada868aa3c164380a5c8ac22af9426e3de6738756430ef239f1c4d8","abstract_canon_sha256":"c105d3d318a788567dd3733ec06382ebbe6e8071cb80a8eaa47faf3fa7cf05c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:34:20.248068Z","signature_b64":"66UZW64uyOPDi8Ult8n741veCNMmO+7AM83L+4PKGXyy6qNpwy8T7vsrNN/ztTGISmBWImOKc43oAeXLdmEkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f96ee1239d572df74ef2321205a02946fdc5fb142ef1193f73eb293d26f4989","last_reissued_at":"2026-08-06T01:34:20.246610Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:34:20.246610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jun Zhou, Tan Zhenwei, Wanli Gu, Wei Chen, Xiaolu Zhang, Yinghao Tang, Yiyao Wang","submitted_at":"2026-08-05T02:31:48Z","abstract_excerpt":"Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery. We introduce FinReportBench, an expert-grounded benchmark for measuring and improving institution-grade financial report generation. Expert review reveals recurring gaps in report identity, institutional components, source discipline, and visual delivery. We derive a 35-item rubric through expert partial orders, multimodal evidence, and audits of decision boundaries, covering deliverability, report identity, and institutional completeness. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04374","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/2608.04374/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":"2608.04374","created_at":"2026-08-06T01:34:20.248414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04374v1","created_at":"2026-08-06T01:34:20.248414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04374","created_at":"2026-08-06T01:34:20.248414+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6LO4ERZ2VZN","created_at":"2026-08-06T01:34:20.248414+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6LO4ERZ2VZN65HP","created_at":"2026-08-06T01:34:20.248414+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6LO4ERZ","created_at":"2026-08-06T01:34:20.248414+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/P6LO4ERZ2VZN65HPEMQSAWQCSR","json":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR.json","graph_json":"https://pith.science/api/pith-number/P6LO4ERZ2VZN65HPEMQSAWQCSR/graph.json","events_json":"https://pith.science/api/pith-number/P6LO4ERZ2VZN65HPEMQSAWQCSR/events.json","paper":"https://pith.science/paper/P6LO4ERZ"},"agent_actions":{"view_html":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR","download_json":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR.json","view_paper":"https://pith.science/paper/P6LO4ERZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04374&json=true","fetch_graph":"https://pith.science/api/pith-number/P6LO4ERZ2VZN65HPEMQSAWQCSR/graph.json","fetch_events":"https://pith.science/api/pith-number/P6LO4ERZ2VZN65HPEMQSAWQCSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR/action/storage_attestation","attest_author":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR/action/author_attestation","sign_citation":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR/action/citation_signature","submit_replication":"https://pith.science/pith/P6LO4ERZ2VZN65HPEMQSAWQCSR/action/replication_record"}},"created_at":"2026-08-06T01:34:20.248414+00:00","updated_at":"2026-08-06T01:34:20.248414+00:00"}