{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S36GHMVDW767ZNJKB3F6GZY6Q2","short_pith_number":"pith:S36GHMVD","schema_version":"1.0","canonical_sha256":"96fc63b2a3b7fdfcb52a0ecbe3671e869cec82bda6a884272bdd6e8dddd4cbdf","source":{"kind":"arxiv","id":"2508.06600","version":1},"attestation_state":"computed","paper":{"title":"BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrew Liu, Crystina Zhang, Haoran Hong, Jimmy Lin, Joshua Green, Kai Zou, Kshama Patel, Luyu Gao, Mingyi Su, Nandan Thakur, Ping Nie, Ruoxi Meng, Sahel Sharifymoghaddam, Shengyao Zhuang, Wenhu Chen, Xinyu Shi, Xueguang Ma, Xuye Liu, Yanxi Li, Zijian Chen","submitted_at":"2025-08-08T17:55:11Z","abstract_excerpt":"Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, "},"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":"2508.06600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T17:55:11Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4e498bef7de96ea26fc417107a184ee7707f15423759a80ee9df911c8ea8f7c4","abstract_canon_sha256":"8ad1dcc6453f80e284d5c68365f3373d9dfc5dcf3931ca8838e1becebe7a25ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:03.333229Z","signature_b64":"usvECCnU0jk5yK0uu/t9vNVwQFx/+2cqFzHd7LYpKo8AIM00M8KQb/uOWiJZOeEANXrgWHalKG6yDHoqwbcbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96fc63b2a3b7fdfcb52a0ecbe3671e869cec82bda6a884272bdd6e8dddd4cbdf","last_reissued_at":"2026-07-05T11:51:03.332648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:03.332648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrew Liu, Crystina Zhang, Haoran Hong, Jimmy Lin, Joshua Green, Kai Zou, Kshama Patel, Luyu Gao, Mingyi Su, Nandan Thakur, Ping Nie, Ruoxi Meng, Sahel Sharifymoghaddam, Shengyao Zhuang, Wenhu Chen, Xinyu Shi, Xueguang Ma, Xuye Liu, Yanxi Li, Zijian Chen","submitted_at":"2025-08-08T17:55:11Z","abstract_excerpt":"Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06600","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/2508.06600/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":"2508.06600","created_at":"2026-07-05T11:51:03.332728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06600v1","created_at":"2026-07-05T11:51:03.332728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06600","created_at":"2026-07-05T11:51:03.332728+00:00"},{"alias_kind":"pith_short_12","alias_value":"S36GHMVDW767","created_at":"2026-07-05T11:51:03.332728+00:00"},{"alias_kind":"pith_short_16","alias_value":"S36GHMVDW767ZNJK","created_at":"2026-07-05T11:51:03.332728+00:00"},{"alias_kind":"pith_short_8","alias_value":"S36GHMVD","created_at":"2026-07-05T11:51:03.332728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00508","citing_title":"When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13608","citing_title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13003","citing_title":"The Illusion of Multi-Agent Advantage","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09916","citing_title":"IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06880","citing_title":"Towards Retrieving Interaction Spaces for Agentic Search","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00508","citing_title":"When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02461","citing_title":"AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31650","citing_title":"ECHO: Prune to act, trace to learn with selective turn memory in agentic RL","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30175","citing_title":"CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27361","citing_title":"Natural Language Query to Configuration for Retrieval Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28721","citing_title":"LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10532","citing_title":"ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05253","citing_title":"EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19932","citing_title":"PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25342","citing_title":"From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12913","citing_title":"Revisiting DAgger in the Era of LLM-Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04949","citing_title":"Learning to Retrieve from Agent Trajectories","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03189","citing_title":"Reflective Context Learning: Studying the Optimization Primitives of Context Space","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09539","citing_title":"TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04018","citing_title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25256","citing_title":"AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05253","citing_title":"EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12890","citing_title":"Towards Long-horizon Agentic Multimodal Search","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2","json":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2.json","graph_json":"https://pith.science/api/pith-number/S36GHMVDW767ZNJKB3F6GZY6Q2/graph.json","events_json":"https://pith.science/api/pith-number/S36GHMVDW767ZNJKB3F6GZY6Q2/events.json","paper":"https://pith.science/paper/S36GHMVD"},"agent_actions":{"view_html":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2","download_json":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2.json","view_paper":"https://pith.science/paper/S36GHMVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06600&json=true","fetch_graph":"https://pith.science/api/pith-number/S36GHMVDW767ZNJKB3F6GZY6Q2/graph.json","fetch_events":"https://pith.science/api/pith-number/S36GHMVDW767ZNJKB3F6GZY6Q2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2/action/storage_attestation","attest_author":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2/action/author_attestation","sign_citation":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2/action/citation_signature","submit_replication":"https://pith.science/pith/S36GHMVDW767ZNJKB3F6GZY6Q2/action/replication_record"}},"created_at":"2026-07-05T11:51:03.332728+00:00","updated_at":"2026-07-05T11:51:03.332728+00:00"}