{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NN7A2P2LSFAGNVOMI4AOH7WBYY","short_pith_number":"pith:NN7A2P2L","schema_version":"1.0","canonical_sha256":"6b7e0d3f4b914066d5cc4700e3fec1c60b38fa5036f056a8b9a3668efc0a90cf","source":{"kind":"arxiv","id":"2508.07999","version":2},"attestation_state":"computed","paper":{"title":"WideSearch: Benchmarking Agentic Broad Info-Seeking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Jiawei Wang, Junjie Zhao, Kai Xiang, Ke Wang, Li Chen, Long Zhang, Ryan Wong, Wenhao Huang, Xuan Zhou, Yan Gao, Yang Wang, Zuo Wang","submitted_at":"2025-08-11T14:03:09Z","abstract_excerpt":"From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such \"wide-context\" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent relia"},"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":"2508.07999","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T14:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"c016cb1fa87c8882850da425d0f299fdb1c8dca208a35f6a20153bb114d194d1","abstract_canon_sha256":"45b50bbe932010555b628acb5e6b83d9436f37a07eeabe9f8722507334ddf10c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:51.434183Z","signature_b64":"2Z/ExgKoCgHCm/91o+O925KK/wyN0vbOv3mO9ReEG0yPBQEwE8Kd/aLmhOdDQ9BVD5EhvOcODEKGMi2xikU8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7e0d3f4b914066d5cc4700e3fec1c60b38fa5036f056a8b9a3668efc0a90cf","last_reissued_at":"2026-07-05T12:00:51.433694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:51.433694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WideSearch: Benchmarking Agentic Broad Info-Seeking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Jiawei Wang, Junjie Zhao, Kai Xiang, Ke Wang, Li Chen, Long Zhang, Ryan Wong, Wenhao Huang, Xuan Zhou, Yan Gao, Yang Wang, Zuo Wang","submitted_at":"2025-08-11T14:03:09Z","abstract_excerpt":"From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search agents powered by LLMs offer a promising solution to liberate humans from this tedious work. However, the capability of these agents to perform such \"wide-context\" collection reliably and completely remains largely unevaluated due to a lack of suitable benchmarks. To bridge this gap, we introduce WideSearch, a new benchmark engineered to evaluate agent relia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07999","kind":"arxiv","version":2},"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/2508.07999/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":"2508.07999","created_at":"2026-07-05T12:00:51.433744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07999v2","created_at":"2026-07-05T12:00:51.433744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07999","created_at":"2026-07-05T12:00:51.433744+00:00"},{"alias_kind":"pith_short_12","alias_value":"NN7A2P2LSFAG","created_at":"2026-07-05T12:00:51.433744+00:00"},{"alias_kind":"pith_short_16","alias_value":"NN7A2P2LSFAGNVOM","created_at":"2026-07-05T12:00:51.433744+00:00"},{"alias_kind":"pith_short_8","alias_value":"NN7A2P2L","created_at":"2026-07-05T12:00:51.433744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27595","citing_title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24468","citing_title":"SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24486","citing_title":"AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27882","citing_title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11926","citing_title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20997","citing_title":"BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22219","citing_title":"SGR-Bench: Benchmarking Search Agents on State-Gated Retrieval","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13168","citing_title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20633","citing_title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27221","citing_title":"Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25256","citing_title":"AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02276","citing_title":"Kimi K2.5: Visual Agentic Intelligence","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14518","citing_title":"Mind DeepResearch Technical Report","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19837","citing_title":"Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY","json":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY.json","graph_json":"https://pith.science/api/pith-number/NN7A2P2LSFAGNVOMI4AOH7WBYY/graph.json","events_json":"https://pith.science/api/pith-number/NN7A2P2LSFAGNVOMI4AOH7WBYY/events.json","paper":"https://pith.science/paper/NN7A2P2L"},"agent_actions":{"view_html":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY","download_json":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY.json","view_paper":"https://pith.science/paper/NN7A2P2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/NN7A2P2LSFAGNVOMI4AOH7WBYY/graph.json","fetch_events":"https://pith.science/api/pith-number/NN7A2P2LSFAGNVOMI4AOH7WBYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY/action/storage_attestation","attest_author":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY/action/author_attestation","sign_citation":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY/action/citation_signature","submit_replication":"https://pith.science/pith/NN7A2P2LSFAGNVOMI4AOH7WBYY/action/replication_record"}},"created_at":"2026-07-05T12:00:51.433744+00:00","updated_at":"2026-07-05T12:00:51.433744+00:00"}