{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VJ25UGWNXNXDEFM2XM7YODMSRU","short_pith_number":"pith:VJ25UGWN","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"},"canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","source":{"kind":"arxiv","id":"2506.11763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11763","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11763v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11763","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"VJ25UGWNXNXD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VJ25UGWNXNXDEFM2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VJ25UGWN","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VJ25UGWNXNXDEFM2XM7YODMSRU","target":"record","payload":{"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"},"canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","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"},"source_kind":"arxiv","source_id":"2506.11763","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SOm4Dwysna48xh4fjp6QLTsbQgZl10R7ouMHb4J2w0BgoKWPYMwuMlH1KZCSGEqpkpHVFZXHq9Tzc0EVoGwaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:04:39.072711Z"},"content_sha256":"f7deaa490625a50ec6ede16debcd038f2e5ada53ffa7f5a5b47748e79894545d","schema_version":"1.0","event_id":"sha256:f7deaa490625a50ec6ede16debcd038f2e5ada53ffa7f5a5b47748e79894545d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VJ25UGWNXNXDEFM2XM7YODMSRU","target":"graph","payload":{"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"},"verdict_id":"0955f400-a456-4404-9685-39e6f7dedc53"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7oqTAjyPnoZxDNsF0L/r2TP4A57wDOX75K+pIj9p2O8uLYF5uWfqmG4b5jnIyPhvzWjoxk5HPX14HY2RuiGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:04:39.073973Z"},"content_sha256":"3c2d3d7f652323ae6f3e76143aa5ab05290202bc994a286890ccbf2c15d491e5","schema_version":"1.0","event_id":"sha256:3c2d3d7f652323ae6f3e76143aa5ab05290202bc994a286890ccbf2c15d491e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/bundle.json","state_url":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T15:04:39Z","links":{"resolver":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU","bundle":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/bundle.json","state":"https://pith.science/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJ25UGWNXNXDEFM2XM7YODMSRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VJ25UGWNXNXDEFM2XM7YODMSRU","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":"ac435ac616e289a2223f5bfea0c46dd657fc5aa9999a47cf319bbb3cdc7134f9","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T13:17:32Z","title_canon_sha256":"3a96bff25666a3568df2e4fd406d47bb61a953c95d6d9a9afbd2665556103b76"},"schema_version":"1.0","source":{"id":"2506.11763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11763","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11763v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11763","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"VJ25UGWNXNXD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VJ25UGWNXNXDEFM2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VJ25UGWN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3c2d3d7f652323ae6f3e76143aa5ab05290202bc994a286890ccbf2c15d491e5","target":"graph","created_at":"2026-05-17T23:38:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents."}],"snapshot_sha256":"35fd12d796583bb09f15ce1846605ec6f5a274bc95e3fcba1a953874884c3c27"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f39c9ba62a02cfd3626ee4571502ea64ac1f310e7755d9f61c63408e27581b27"},"paper":{"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","authors_text":"Benfeng Xu, Chiwei Zhu, Mingxuan Du, Xiaorui Wang, Zhendong Mao","cross_cats":["cs.IR"],"headline":"DeepResearch Bench supplies 100 PhD-level tasks across 22 fields plus two evaluation methods that align with human judgment for deep research agents.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T13:17:32Z","title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"},"references":{"count":66,"internal_anchors":19,"resolved_work":66,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"2408.07055 , archiveprefix =","work_id":"7b17f534-444c-40c9-8c05-ead22c892088","year":2024},{"cited_arxiv_id":"2410.07095","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Mle-bench: Evaluating machine learning agents on machine learning engineering","work_id":"a671e43f-ceab-49e7-adc3-473d802a97ca","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"ScienceAgentBench: Toward rigorous assessment of language agents for data-driven scientific discovery","work_id":"e1160394-4fe6-4475-9753-e69ad39fb09e","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"deepseek-ai/DeepSeek-V3-0324 · Hugging Face, March 2025","work_id":"1a4c634b-d889-4f66-a3ba-0c5b087bfefa","year":2025},{"cited_arxiv_id":"2501.12948","doi":"","is_internal_anchor":true,"ref_index":5,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025}],"snapshot_sha256":"5dcc6e48560925ff898e2a401bf2b79a5a41525f45dcff962f90abe25c56cb88"},"source":{"id":"2506.11763","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T08:04:42.628782Z","id":"0955f400-a456-4404-9685-39e6f7dedc53","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"0955f400-a456-4404-9685-39e6f7dedc53"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f7deaa490625a50ec6ede16debcd038f2e5ada53ffa7f5a5b47748e79894545d","target":"record","created_at":"2026-05-17T23:38:48Z","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":"ac435ac616e289a2223f5bfea0c46dd657fc5aa9999a47cf319bbb3cdc7134f9","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-13T13:17:32Z","title_canon_sha256":"3a96bff25666a3568df2e4fd406d47bb61a953c95d6d9a9afbd2665556103b76"},"schema_version":"1.0","source":{"id":"2506.11763","kind":"arxiv","version":1}},"canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa75da1acdbb6e32159abb3f870d928d33da2195ace29d4b094e865f5e65104b","first_computed_at":"2026-05-17T23:38:48.555402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.555402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WdupR/ml643Ak+ypqbU/VYs8XFv242CELF4spqFrpDfIYQt0733Jzgrr+WjUCXXk4dVexF205/1ikhZ9KWy3AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.555924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7deaa490625a50ec6ede16debcd038f2e5ada53ffa7f5a5b47748e79894545d","sha256:3c2d3d7f652323ae6f3e76143aa5ab05290202bc994a286890ccbf2c15d491e5"],"state_sha256":"b482c012635490fb469404dbd236ce744db1e558b71b84eab267483d18c19555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGbvgro6PluRwXVZqXIo6gc/2Bhw8ADsqVCmOmr1mPCGS+QENRou4YH1FcOjHRC7VKLHfeSJOJEhsc9WV8oMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T15:04:39.079720Z","bundle_sha256":"a2f0d606e1702063edf611ed79edd40cde3857777b18e2d4551381566bc835ea"}}