{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYCUNBYMUS2CCS7RNEZAF4ZIVR","short_pith_number":"pith:WYCUNBYM","schema_version":"1.0","canonical_sha256":"b60546870ca4b4214bf1693202f328ac6522d0615f35afe557f4bd59fc217117","source":{"kind":"arxiv","id":"2606.02404","version":1},"attestation_state":"computed","paper":{"title":"K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyoon Lee, Dayoon Ko, Dongkeun Yoon, Eunsu Kim, Geewook Kim, Guijin Son, Haneul Yoo, Jaewon Cho, Jaeyeon Kim, Jeonghun Park, Junghun Park, Kyochul Jang, Nahyun Lee, Seungone Kim, Woojin Cho","submitted_at":"2026-06-01T15:50:03Z","abstract_excerpt":"Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks remain scarce. We introduce K-BrowseComp, a web-browsing agent benchmark grounded in Korean contexts, consisting of 400 problems. The 300-problem K-BrowseComp-Verified subset is manually constructed and validated by native Korean speakers. On this subset, frontier LLMs, including GPT-5.5, DeepSeek-V4-Pro, and GLM-5.1, reach only 30.00--45.67\\%, a substantial drop from BrowseComp, while Korean LLMs released through K"},"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":"2606.02404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T15:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"cb08abc0f5efa54cc9b2a702658dc8d2a3d655d8361f063e8dfb4e29537f9fbc","abstract_canon_sha256":"7fc4e71737583c1f3036e2bb238f55816db50d1bdb5bd1950fd53a0e7b453838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:58.374728Z","signature_b64":"Jx3gTsBidDl282D+0ckOu1zFkGq5mn5GsA7vV2jRLXVvpZWATKSwgPdYw1pvZ+60+lq79N2tqSul9HC8J6cFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b60546870ca4b4214bf1693202f328ac6522d0615f35afe557f4bd59fc217117","last_reissued_at":"2026-06-02T03:04:58.374277Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:58.374277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyoon Lee, Dayoon Ko, Dongkeun Yoon, Eunsu Kim, Geewook Kim, Guijin Son, Haneul Yoo, Jaewon Cho, Jaeyeon Kim, Jeonghun Park, Junghun Park, Kyochul Jang, Nahyun Lee, Seungone Kim, Woojin Cho","submitted_at":"2026-06-01T15:50:03Z","abstract_excerpt":"Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks remain scarce. We introduce K-BrowseComp, a web-browsing agent benchmark grounded in Korean contexts, consisting of 400 problems. The 300-problem K-BrowseComp-Verified subset is manually constructed and validated by native Korean speakers. On this subset, frontier LLMs, including GPT-5.5, DeepSeek-V4-Pro, and GLM-5.1, reach only 30.00--45.67\\%, a substantial drop from BrowseComp, while Korean LLMs released through K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02404","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/2606.02404/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":"2606.02404","created_at":"2026-06-02T03:04:58.374359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02404v1","created_at":"2026-06-02T03:04:58.374359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02404","created_at":"2026-06-02T03:04:58.374359+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYCUNBYMUS2C","created_at":"2026-06-02T03:04:58.374359+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYCUNBYMUS2CCS7R","created_at":"2026-06-02T03:04:58.374359+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYCUNBYM","created_at":"2026-06-02T03:04:58.374359+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/WYCUNBYMUS2CCS7RNEZAF4ZIVR","json":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR.json","graph_json":"https://pith.science/api/pith-number/WYCUNBYMUS2CCS7RNEZAF4ZIVR/graph.json","events_json":"https://pith.science/api/pith-number/WYCUNBYMUS2CCS7RNEZAF4ZIVR/events.json","paper":"https://pith.science/paper/WYCUNBYM"},"agent_actions":{"view_html":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR","download_json":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR.json","view_paper":"https://pith.science/paper/WYCUNBYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02404&json=true","fetch_graph":"https://pith.science/api/pith-number/WYCUNBYMUS2CCS7RNEZAF4ZIVR/graph.json","fetch_events":"https://pith.science/api/pith-number/WYCUNBYMUS2CCS7RNEZAF4ZIVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR/action/storage_attestation","attest_author":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR/action/author_attestation","sign_citation":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR/action/citation_signature","submit_replication":"https://pith.science/pith/WYCUNBYMUS2CCS7RNEZAF4ZIVR/action/replication_record"}},"created_at":"2026-06-02T03:04:58.374359+00:00","updated_at":"2026-06-02T03:04:58.374359+00:00"}