{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUGS44T4JFBN6KU3JVULLLGF4J","short_pith_number":"pith:NUGS44T4","schema_version":"1.0","canonical_sha256":"6d0d2e727c4942df2a9b4d68b5acc5e24207bae8e72f474c12cf2a1b15972f46","source":{"kind":"arxiv","id":"2606.12837","version":1},"attestation_state":"computed","paper":{"title":"LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiarui Zhao, Lingchuan Liu, Rongzhi Zhang, Xi Su, Xunliang Cai","submitted_at":"2026-06-11T03:04:32Z","abstract_excerpt":"Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipelin"},"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":"2606.12837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T03:04:32Z","cross_cats_sorted":[],"title_canon_sha256":"c433ad667a82ce42c4ef0854a6800f83689c95b54a127fdbe49b5654bf9e88bc","abstract_canon_sha256":"d53f093dec5e692652523d9e215916756e6f808fb1204d29951bbe37cf72a58b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:53.491242Z","signature_b64":"i93RLQF9YgmajoyJnjr8bYgJYgGQOTwq/vhxPXiYvbO/wY8WrCSXIxWQ23ChK7kFZmTSR3TUl6cWINcQmtu3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d0d2e727c4942df2a9b4d68b5acc5e24207bae8e72f474c12cf2a1b15972f46","last_reissued_at":"2026-06-12T01:08:53.490445Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:53.490445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiarui Zhao, Lingchuan Liu, Rongzhi Zhang, Xi Su, Xunliang Cai","submitted_at":"2026-06-11T03:04:32Z","abstract_excerpt":"Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12837","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/2606.12837/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":"2606.12837","created_at":"2026-06-12T01:08:53.490569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12837v1","created_at":"2026-06-12T01:08:53.490569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12837","created_at":"2026-06-12T01:08:53.490569+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUGS44T4JFBN","created_at":"2026-06-12T01:08:53.490569+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUGS44T4JFBN6KU3","created_at":"2026-06-12T01:08:53.490569+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUGS44T4","created_at":"2026-06-12T01:08:53.490569+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/NUGS44T4JFBN6KU3JVULLLGF4J","json":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J.json","graph_json":"https://pith.science/api/pith-number/NUGS44T4JFBN6KU3JVULLLGF4J/graph.json","events_json":"https://pith.science/api/pith-number/NUGS44T4JFBN6KU3JVULLLGF4J/events.json","paper":"https://pith.science/paper/NUGS44T4"},"agent_actions":{"view_html":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J","download_json":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J.json","view_paper":"https://pith.science/paper/NUGS44T4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12837&json=true","fetch_graph":"https://pith.science/api/pith-number/NUGS44T4JFBN6KU3JVULLLGF4J/graph.json","fetch_events":"https://pith.science/api/pith-number/NUGS44T4JFBN6KU3JVULLLGF4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J/action/storage_attestation","attest_author":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J/action/author_attestation","sign_citation":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J/action/citation_signature","submit_replication":"https://pith.science/pith/NUGS44T4JFBN6KU3JVULLLGF4J/action/replication_record"}},"created_at":"2026-06-12T01:08:53.490569+00:00","updated_at":"2026-06-12T01:08:53.490569+00:00"}