{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J74XWQNW25KC7WFSH34FTHUX4M","short_pith_number":"pith:J74XWQNW","schema_version":"1.0","canonical_sha256":"4ff97b41b6d7542fd8b23ef8599e97e32372aa688be6ed487ad1676da78f22f9","source":{"kind":"arxiv","id":"2606.03918","version":1},"attestation_state":"computed","paper":{"title":"Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alice Lu, Andy Lyu, Eric Cho, Shawn Huang","submitted_at":"2026-06-02T17:11:56Z","abstract_excerpt":"AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The harder, more valuable challenge is reasoning through the open-ended questions that define expert Analyst work. Existing benchmarks do not capture this class of problem, and those that attempt to evaluate open-ended reasoning rely on model-judged outputs that introduce noise and circularity. We present Hedge-Bench 1.0: a benchmark of 102 actual, on-the-job tasks grounded in the explicit reasoning traces of professional hedge fund analysts working w"},"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":"2606.03918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T17:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"e8f0bcc884f9a14e497563a9201c1e3139d3477727d6241509a9b9c20ddde375","abstract_canon_sha256":"59c4f2c1fdbdf531480d34a04c4d4bc697531d28e897f1fb46f73e0dbea1086a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:06.858491Z","signature_b64":"MvJoTNPHPR6vCnwzB5YlKjo0ABORYzUVsuazfOFP7zg21ftQpWVNRFUngs9BPbdEeGH36WwGWmsx82hEBPDsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff97b41b6d7542fd8b23ef8599e97e32372aa688be6ed487ad1676da78f22f9","last_reissued_at":"2026-06-03T02:06:06.858073Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:06.858073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alice Lu, Andy Lyu, Eric Cho, Shawn Huang","submitted_at":"2026-06-02T17:11:56Z","abstract_excerpt":"AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The harder, more valuable challenge is reasoning through the open-ended questions that define expert Analyst work. Existing benchmarks do not capture this class of problem, and those that attempt to evaluate open-ended reasoning rely on model-judged outputs that introduce noise and circularity. We present Hedge-Bench 1.0: a benchmark of 102 actual, on-the-job tasks grounded in the explicit reasoning traces of professional hedge fund analysts working w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03918","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/2606.03918/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":"2606.03918","created_at":"2026-06-03T02:06:06.858145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03918v1","created_at":"2026-06-03T02:06:06.858145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03918","created_at":"2026-06-03T02:06:06.858145+00:00"},{"alias_kind":"pith_short_12","alias_value":"J74XWQNW25KC","created_at":"2026-06-03T02:06:06.858145+00:00"},{"alias_kind":"pith_short_16","alias_value":"J74XWQNW25KC7WFS","created_at":"2026-06-03T02:06:06.858145+00:00"},{"alias_kind":"pith_short_8","alias_value":"J74XWQNW","created_at":"2026-06-03T02:06:06.858145+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/J74XWQNW25KC7WFSH34FTHUX4M","json":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M.json","graph_json":"https://pith.science/api/pith-number/J74XWQNW25KC7WFSH34FTHUX4M/graph.json","events_json":"https://pith.science/api/pith-number/J74XWQNW25KC7WFSH34FTHUX4M/events.json","paper":"https://pith.science/paper/J74XWQNW"},"agent_actions":{"view_html":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M","download_json":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M.json","view_paper":"https://pith.science/paper/J74XWQNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03918&json=true","fetch_graph":"https://pith.science/api/pith-number/J74XWQNW25KC7WFSH34FTHUX4M/graph.json","fetch_events":"https://pith.science/api/pith-number/J74XWQNW25KC7WFSH34FTHUX4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M/action/storage_attestation","attest_author":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M/action/author_attestation","sign_citation":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M/action/citation_signature","submit_replication":"https://pith.science/pith/J74XWQNW25KC7WFSH34FTHUX4M/action/replication_record"}},"created_at":"2026-06-03T02:06:06.858145+00:00","updated_at":"2026-06-03T02:06:06.858145+00:00"}