{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VJ25UGWNXNXDEFM2XM7YODMSRU","short_pith_number":"pith:VJ25UGWN","schema_version":"1.0","canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","source":{"kind":"arxiv","id":"2506.11763","version":1},"attestation_state":"computed","paper":{"title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents.","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Chiwei Zhu, Mingxuan Du, Xiaorui Wang, Zhendong Mao","submitted_at":"2025-06-13T13:17:32Z","abstract_excerpt":"Deep Research Agents are a prominent category of LLM-based agents. By autonomously orchestrating multistep web exploration, targeted retrieval, and higher-order synthesis, they transform vast amounts of online information into analyst-grade, citation-rich reports--compressing hours of manual desk research into minutes. However, a comprehensive benchmark for systematically evaluating the capabilities of these agents remains absent. To bridge this gap, we present DeepResearch Bench, a benchmark consisting of 100 PhD-level research tasks, each meticulously crafted by domain experts across 22 dist"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2506.11763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T13:17:32Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3a96bff25666a3568df2e4fd406d47bb61a953c95d6d9a9afbd2665556103b76","abstract_canon_sha256":"ac435ac616e289a2223f5bfea0c46dd657fc5aa9999a47cf319bbb3cdc7134f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.555924Z","signature_b64":"WdupR/ml643Ak+ypqbU/VYs8XFv242CELF4spqFrpDfIYQt0733Jzgrr+WjUCXXk4dVexF205/1ikhZ9KWy3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","last_reissued_at":"2026-05-17T23:38:48.555402Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.555402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents.","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Chiwei Zhu, Mingxuan Du, Xiaorui Wang, Zhendong Mao","submitted_at":"2025-06-13T13:17:32Z","abstract_excerpt":"Deep Research Agents are a prominent category of LLM-based agents. By autonomously orchestrating multistep web exploration, targeted retrieval, and higher-order synthesis, they transform vast amounts of online information into analyst-grade, citation-rich reports--compressing hours of manual desk research into minutes. However, a comprehensive benchmark for systematically evaluating the capabilities of these agents remains absent. To bridge this gap, we present DeepResearch Bench, a benchmark consisting of 100 PhD-level research tasks, each meticulously crafted by domain experts across 22 dist"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present DeepResearch Bench, a benchmark consisting of 100 PhD-level research tasks... We therefore propose two novel methodologies that achieve strong alignment with human judgment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 100 tasks crafted by domain experts across 22 fields are representative of real deep-research challenges and the two proposed evaluation methodologies genuinely align with human judgment without introducing systematic bias or requiring undisclosed tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"35fd12d796583bb09f15ce1846605ec6f5a274bc95e3fcba1a953874884c3c27"},"source":{"id":"2506.11763","kind":"arxiv","version":1},"verdict":{"id":"0955f400-a456-4404-9685-39e6f7dedc53","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:04:42.628782Z","strongest_claim":"We present DeepResearch Bench, a benchmark consisting of 100 PhD-level research tasks... We therefore propose two novel methodologies that achieve strong alignment with human judgment.","one_line_summary":"DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 100 tasks crafted by domain experts across 22 fields are representative of real deep-research challenges and the two proposed evaluation methodologies genuinely align with human judgment without introducing systematic bias or requiring undisclosed tuning.","pith_extraction_headline":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents."},"references":{"count":66,"sample":[{"doi":"","year":2024,"title":"2408.07055 , archiveprefix =","work_id":"7b17f534-444c-40c9-8c05-ead22c892088","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Mle-bench: Evaluating machine learning agents on machine learning engineering","work_id":"a671e43f-ceab-49e7-adc3-473d802a97ca","ref_index":2,"cited_arxiv_id":"2410.07095","is_internal_anchor":true},{"doi":"","year":2025,"title":"ScienceAgentBench: Toward rigorous assessment of language agents for data-driven scientific discovery","work_id":"e1160394-4fe6-4475-9753-e69ad39fb09e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"deepseek-ai/DeepSeek-V3-0324 · Hugging Face, March 2025","work_id":"1a4c634b-d889-4f66-a3ba-0c5b087bfefa","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":5,"cited_arxiv_id":"2501.12948","is_internal_anchor":true}],"resolved_work":66,"snapshot_sha256":"5dcc6e48560925ff898e2a401bf2b79a5a41525f45dcff962f90abe25c56cb88","internal_anchors":19},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f39c9ba62a02cfd3626ee4571502ea64ac1f310e7755d9f61c63408e27581b27"},"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":"2506.11763","created_at":"2026-05-17T23:38:48.555493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11763v1","created_at":"2026-05-17T23:38:48.555493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11763","created_at":"2026-05-17T23:38:48.555493+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ25UGWNXNXD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ25UGWNXNXDEFM2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ25UGWN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2605.23590","citing_title":"Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21413","citing_title":"Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21413","citing_title":"Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21413","citing_title":"Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21413","citing_title":"Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17554","citing_title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18421","citing_title":"EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19196","citing_title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17324","citing_title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13024","citing_title":"WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09554","citing_title":"LABBench2: An Improved Benchmark for AI Systems Performing Biology Research","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.05912","citing_title":"DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20633","citing_title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13034","citing_title":"ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":248,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03173","citing_title":"Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26235","citing_title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08366","citing_title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10899","citing_title":"RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10530","citing_title":"Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU","json":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU.json","graph_json":"https://pith.science/api/pith-number/VJ25UGWNXNXDEFM2XM7YODMSRU/graph.json","events_json":"https://pith.science/api/pith-number/VJ25UGWNXNXDEFM2XM7YODMSRU/events.json","paper":"https://pith.science/paper/VJ25UGWN"},"agent_actions":{"view_html":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU","download_json":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU.json","view_paper":"https://pith.science/paper/VJ25UGWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11763&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ25UGWNXNXDEFM2XM7YODMSRU/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ25UGWNXNXDEFM2XM7YODMSRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/action/storage_attestation","attest_author":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/action/author_attestation","sign_citation":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/action/citation_signature","submit_replication":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/action/replication_record"}},"created_at":"2026-05-17T23:38:48.555493+00:00","updated_at":"2026-05-17T23:38:48.555493+00:00"}