{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MXAUWQ6IRVAVGWMVUE5EP45WPM","short_pith_number":"pith:MXAUWQ6I","schema_version":"1.0","canonical_sha256":"65c14b43c88d41535995a13a47f3b67b34bd63b10bd5f464bb16e476d6a6318b","source":{"kind":"arxiv","id":"2605.17554","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aman Saksena, Divyansh Sahu, Tanmay Asthana","submitted_at":"2026-05-17T17:32:52Z","abstract_excerpt":"Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand. They are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, missing the multi-document, decision-grade work DRAs are deployed to produce. We introduce a benchmark targeting the structured analytical deliverables that fill a management consultant's typical week.\n  We grade three frontier agents, namely Claude Opus 4.6 with web search, OpenAI o3-deep-res"},"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":"2605.17554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T17:32:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af72164c678330ecf1bc9e56063a94ef6958b05859230e91c81097f42a569bd8","abstract_canon_sha256":"e22f6c995cfc738dabc25581f0bd34a1665d2646bcb969706211a3682267362c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:45.461828Z","signature_b64":"6yhcDF8j81AJLfwnV2x74NIX6jJAjIZmGVOI/IvEYV+i9vJBPpBuw4t90xBzeRFkv1sNGJCKzqJwSM7qyaa3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c14b43c88d41535995a13a47f3b67b34bd63b10bd5f464bb16e476d6a6318b","last_reissued_at":"2026-05-20T00:04:45.460846Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:45.460846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Aman Saksena, Divyansh Sahu, Tanmay Asthana","submitted_at":"2026-05-17T17:32:52Z","abstract_excerpt":"Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand. They are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, missing the multi-document, decision-grade work DRAs are deployed to produce. We introduce a benchmark targeting the structured analytical deliverables that fill a management consultant's typical week.\n  We grade three frontier agents, namely Claude Opus 4.6 with web search, OpenAI o3-deep-res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17554","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/2605.17554/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.605579Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.539251Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"492ff49601fd25e8b0440ef023112fb9acf2d56371e65d2dc0402f1f8c0528c5"},"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":"2605.17554","created_at":"2026-05-20T00:04:45.460994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17554v1","created_at":"2026-05-20T00:04:45.460994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17554","created_at":"2026-05-20T00:04:45.460994+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXAUWQ6IRVAV","created_at":"2026-05-20T00:04:45.460994+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXAUWQ6IRVAVGWMV","created_at":"2026-05-20T00:04:45.460994+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXAUWQ6I","created_at":"2026-05-20T00:04:45.460994+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/MXAUWQ6IRVAVGWMVUE5EP45WPM","json":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM.json","graph_json":"https://pith.science/api/pith-number/MXAUWQ6IRVAVGWMVUE5EP45WPM/graph.json","events_json":"https://pith.science/api/pith-number/MXAUWQ6IRVAVGWMVUE5EP45WPM/events.json","paper":"https://pith.science/paper/MXAUWQ6I"},"agent_actions":{"view_html":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM","download_json":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM.json","view_paper":"https://pith.science/paper/MXAUWQ6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17554&json=true","fetch_graph":"https://pith.science/api/pith-number/MXAUWQ6IRVAVGWMVUE5EP45WPM/graph.json","fetch_events":"https://pith.science/api/pith-number/MXAUWQ6IRVAVGWMVUE5EP45WPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM/action/storage_attestation","attest_author":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM/action/author_attestation","sign_citation":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM/action/citation_signature","submit_replication":"https://pith.science/pith/MXAUWQ6IRVAVGWMVUE5EP45WPM/action/replication_record"}},"created_at":"2026-05-20T00:04:45.460994+00:00","updated_at":"2026-05-20T00:04:45.460994+00:00"}