{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GYUZJQ4YWIY62KRFI5PIXAGCOL","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":"5bcc1b76529d2263a471f43d0aac1d34ec400304a7f22bae6da4b08155d4e839","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:22:08Z","title_canon_sha256":"abb590eaa4c4371ff68fdc44a002ddc4395ba20f63acc202804a2cd9b04f36f0"},"schema_version":"1.0","source":{"id":"2311.09797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09797","created_at":"2026-07-05T08:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09797v2","created_at":"2026-07-05T08:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09797","created_at":"2026-07-05T08:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"GYUZJQ4YWIY6","created_at":"2026-07-05T08:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"GYUZJQ4YWIY62KRF","created_at":"2026-07-05T08:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"GYUZJQ4Y","created_at":"2026-07-05T08:53:18Z"}],"graph_snapshots":[{"event_id":"sha256:7f9105ad39275b85797183c4672d4e6afed6e478f77bd13a0bc5dd4c50ed3626","target":"graph","created_at":"2026-07-05T08:53:18Z","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/2311.09797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce FinanceMath, a novel benchmark designed to evaluate LLMs' capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, FinanceMath includes 1,200 problems with a hybrid of textual and tabular content. These problems require college-level knowledge in the finance domain for effective resolution. Second, we provide expert-annotated, detailed solution references in Python program format, ensuring a high-quality benchmark for LLM assessment. We also construct a finance-domain knowledge bank and invest","authors_text":"Arman Cohan, Chen Zhao, Hongjun Liu, Rui Zhang, Yilun Zhao, Yitao Long","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:22:08Z","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09797","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:a3e7159df0f29f5c122457ba3c8c8f7e0551a5007f8115fc3d37d895946b7784","target":"record","created_at":"2026-07-05T08:53:18Z","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":"5bcc1b76529d2263a471f43d0aac1d34ec400304a7f22bae6da4b08155d4e839","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:22:08Z","title_canon_sha256":"abb590eaa4c4371ff68fdc44a002ddc4395ba20f63acc202804a2cd9b04f36f0"},"schema_version":"1.0","source":{"id":"2311.09797","kind":"arxiv","version":2}},"canonical_sha256":"362994c398b231ed2a25475e8b80c272e18938dfcbce6b6beeadf68ecc79438e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"362994c398b231ed2a25475e8b80c272e18938dfcbce6b6beeadf68ecc79438e","first_computed_at":"2026-07-05T08:53:18.313442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:18.313442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EZVOpO0KEvCwDU9UVQEdJXEW9psrT3hH0U2SMamaXICTphB99ptU/kuMmeRGdZc06jvcJx7Qm01F/ZxHlaQlBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:18.313973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3e7159df0f29f5c122457ba3c8c8f7e0551a5007f8115fc3d37d895946b7784","sha256:7f9105ad39275b85797183c4672d4e6afed6e478f77bd13a0bc5dd4c50ed3626"],"state_sha256":"f141e31bda48a5ad3c46b179f69c86eb8a7a20fef06213c6810153a6350dbd18"}