{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I3M7YRWFOR4ZDV34V5NP6KGYXC","short_pith_number":"pith:I3M7YRWF","schema_version":"1.0","canonical_sha256":"46d9fc46c5747991d77caf5aff28d8b885ed8bf271d43561eef7dcf7e5d2ae80","source":{"kind":"arxiv","id":"2608.11683","version":1},"attestation_state":"computed","paper":{"title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arash Alidoust, Ashwin Paranjape, O. Ozan Koyluoglu, Richard Diehl Martinez, Thejas Venkatesh, Vishank Bhatia, Yuhao Zhang","submitted_at":"2026-08-12T05:43:26Z","abstract_excerpt":"AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand. We introduce FrontierFinance, a fully open benchmark of 220 expert-crafted queries and 11,543 source-attributed rubrics spanning six crucial use cases across the full investor workflow. F"},"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":"2608.11683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T05:43:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6739dcee7e3eef5b96a0431ab1e7180e9ce076f3b0079da8a93a2288fcc35895","abstract_canon_sha256":"1155dd66a67a2a97ef856e59125ab3e2fc72e8a6ff8e655a2fb5d8eef0867888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:49.674888Z","signature_b64":"6nbQALE5wciwgMW3M4Gn+PnFyXKUZGkgp4Fh1QdyFBVV2gH2cJf9vL1FM4LTH4yl6eFwzS/jq0vp7RQr4wjeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d9fc46c5747991d77caf5aff28d8b885ed8bf271d43561eef7dcf7e5d2ae80","last_reissued_at":"2026-08-13T01:27:49.672808Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:49.672808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arash Alidoust, Ashwin Paranjape, O. Ozan Koyluoglu, Richard Diehl Martinez, Thejas Venkatesh, Vishank Bhatia, Yuhao Zhang","submitted_at":"2026-08-12T05:43:26Z","abstract_excerpt":"AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand. We introduce FrontierFinance, a fully open benchmark of 220 expert-crafted queries and 11,543 source-attributed rubrics spanning six crucial use cases across the full investor workflow. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11683","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/2608.11683/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":"2608.11683","created_at":"2026-08-13T01:27:49.673892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11683v1","created_at":"2026-08-13T01:27:49.673892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11683","created_at":"2026-08-13T01:27:49.673892+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3M7YRWFOR4Z","created_at":"2026-08-13T01:27:49.673892+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3M7YRWFOR4ZDV34","created_at":"2026-08-13T01:27:49.673892+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3M7YRWF","created_at":"2026-08-13T01:27:49.673892+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/I3M7YRWFOR4ZDV34V5NP6KGYXC","json":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC.json","graph_json":"https://pith.science/api/pith-number/I3M7YRWFOR4ZDV34V5NP6KGYXC/graph.json","events_json":"https://pith.science/api/pith-number/I3M7YRWFOR4ZDV34V5NP6KGYXC/events.json","paper":"https://pith.science/paper/I3M7YRWF"},"agent_actions":{"view_html":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC","download_json":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC.json","view_paper":"https://pith.science/paper/I3M7YRWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11683&json=true","fetch_graph":"https://pith.science/api/pith-number/I3M7YRWFOR4ZDV34V5NP6KGYXC/graph.json","fetch_events":"https://pith.science/api/pith-number/I3M7YRWFOR4ZDV34V5NP6KGYXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC/action/storage_attestation","attest_author":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC/action/author_attestation","sign_citation":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC/action/citation_signature","submit_replication":"https://pith.science/pith/I3M7YRWFOR4ZDV34V5NP6KGYXC/action/replication_record"}},"created_at":"2026-08-13T01:27:49.673892+00:00","updated_at":"2026-08-13T01:27:49.673892+00:00"}