{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2ZU4CENAEK5M2NYRHTHTGLECZ6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"446d53f42c45112888df2a098ba4c3f7bd907bd7943b962d077cd27074c384dd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-10T02:51:53Z","title_canon_sha256":"8a4347e3769239666bd60e74d915aa76132b09be0eb024f5f78479c2cc291a9f"},"schema_version":"1.0","source":{"id":"2601.06401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06401","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06401v2","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06401","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"2ZU4CENAEK5M","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"2ZU4CENAEK5M2NYR","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"2ZU4CENA","created_at":"2026-07-14T01:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:d39f352806e14a63ee387bbb1ddc5a93566602e7945aff92773ae60055f34c06","target":"graph","created_at":"2026-07-14T01:22:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.06401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are becoming increasingly significant in financial applications. Nevertheless, prevailing benchmarks are largely dependent on simulated or generic data, which leads to a significant gap between reported performance and actual efficacy in real-world scenarios. To tackle this challenge, we present BizFinBench.v2, the first integrated offline and online benchmark built upon authentic user query-response data from both Chinese and U.S. equity markets. It comprises 28,860 questions across eight offline and two online tasks. Experimental results show that GPT-5 achieves a mere ","authors_text":"Guilong Lu, Liwen Zhang, Rongjunchen Zhang, Shuai Jia, Xin Guo, Xuntao Guo, Zhi Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-10T02:51:53Z","title":"BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06401","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80f6a8494740a15feefcd9859217f495345bf7d3a23df91da7417d5efb6e5233","target":"record","created_at":"2026-07-14T01:22:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"446d53f42c45112888df2a098ba4c3f7bd907bd7943b962d077cd27074c384dd","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-10T02:51:53Z","title_canon_sha256":"8a4347e3769239666bd60e74d915aa76132b09be0eb024f5f78479c2cc291a9f"},"schema_version":"1.0","source":{"id":"2601.06401","kind":"arxiv","version":2}},"canonical_sha256":"d669c111a022bacd37113ccf332c82cfb2a985dc2dc18df9d8f09f3d4b219ec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d669c111a022bacd37113ccf332c82cfb2a985dc2dc18df9d8f09f3d4b219ec8","first_computed_at":"2026-07-14T01:22:03.083297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:03.083297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ffC8C2clq9LRZluhNHO0F1mAhfkUGhcQWZBSyWwp5g5Q0CqAML3xcHpSE2fR16ACjsy/1VJfyXGHnCjZwO75Bw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:03.084295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80f6a8494740a15feefcd9859217f495345bf7d3a23df91da7417d5efb6e5233","sha256:d39f352806e14a63ee387bbb1ddc5a93566602e7945aff92773ae60055f34c06"],"state_sha256":"0bf719c099821bca578cdc524adaa3245d4a82259efd0fe899ccbfee36350813"}