{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZHU2RJQPVU5IFE5XPN4HXPMIU","short_pith_number":"pith:SZHU2RJQ","schema_version":"1.0","canonical_sha256":"964f4d45307d69d4149dbbdbc3ddec4519f0425aa012d4ca703855109a5b2ac1","source":{"kind":"arxiv","id":"2505.15372","version":1},"attestation_state":"computed","paper":{"title":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Libo Qin, Mengkang Hu, Peng Wang, Qiguang Chen, Ruihan Tao","submitted_at":"2025-05-21T11:07:02Z","abstract_excerpt":"Recently, large language model (LLM)-based agents have achieved significant success in interactive environments, attracting significant academic and industrial attention. Despite these advancements, current research predominantly focuses on English scenarios. In reality, there are over 7,000 languages worldwide, all of which demand access to comparable agentic services. Nevertheless, the development of language agents remains inadequate for meeting the diverse requirements of multilingual agentic applications. To fill this gap, we introduce X-WebAgentBench, a novel multilingual agent benchmark"},"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":"2505.15372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T11:07:02Z","cross_cats_sorted":[],"title_canon_sha256":"9532c76bd5af1213d3c18835ef668f2f983dcccf2c2cecab6618df08b116c358","abstract_canon_sha256":"96b5d8b36ef06b41fd91b318b91e7c353cefd89fed173625a6cf5557dc2b5c9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:44.362588Z","signature_b64":"nN6KuAnqJKnSS6Ssw4PUthvH5HzmYTtPtH7mzTfFW6zvQOibnFbgL31RtgdWNFxIywzfkg/9dBRzIuyCDRdvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"964f4d45307d69d4149dbbdbc3ddec4519f0425aa012d4ca703855109a5b2ac1","last_reissued_at":"2026-07-05T11:06:44.362066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:44.362066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Libo Qin, Mengkang Hu, Peng Wang, Qiguang Chen, Ruihan Tao","submitted_at":"2025-05-21T11:07:02Z","abstract_excerpt":"Recently, large language model (LLM)-based agents have achieved significant success in interactive environments, attracting significant academic and industrial attention. Despite these advancements, current research predominantly focuses on English scenarios. In reality, there are over 7,000 languages worldwide, all of which demand access to comparable agentic services. Nevertheless, the development of language agents remains inadequate for meeting the diverse requirements of multilingual agentic applications. To fill this gap, we introduce X-WebAgentBench, a novel multilingual agent benchmark"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15372","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/2505.15372/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":"2505.15372","created_at":"2026-07-05T11:06:44.362129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15372v1","created_at":"2026-07-05T11:06:44.362129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15372","created_at":"2026-07-05T11:06:44.362129+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZHU2RJQPVU5","created_at":"2026-07-05T11:06:44.362129+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZHU2RJQPVU5IFE5","created_at":"2026-07-05T11:06:44.362129+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZHU2RJQ","created_at":"2026-07-05T11:06:44.362129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":159,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU","json":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU.json","graph_json":"https://pith.science/api/pith-number/SZHU2RJQPVU5IFE5XPN4HXPMIU/graph.json","events_json":"https://pith.science/api/pith-number/SZHU2RJQPVU5IFE5XPN4HXPMIU/events.json","paper":"https://pith.science/paper/SZHU2RJQ"},"agent_actions":{"view_html":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU","download_json":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU.json","view_paper":"https://pith.science/paper/SZHU2RJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15372&json=true","fetch_graph":"https://pith.science/api/pith-number/SZHU2RJQPVU5IFE5XPN4HXPMIU/graph.json","fetch_events":"https://pith.science/api/pith-number/SZHU2RJQPVU5IFE5XPN4HXPMIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU/action/storage_attestation","attest_author":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU/action/author_attestation","sign_citation":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU/action/citation_signature","submit_replication":"https://pith.science/pith/SZHU2RJQPVU5IFE5XPN4HXPMIU/action/replication_record"}},"created_at":"2026-07-05T11:06:44.362129+00:00","updated_at":"2026-07-05T11:06:44.362129+00:00"}