{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SZDEZMHJW7WQ4WCCDAL4FDIHZD","short_pith_number":"pith:SZDEZMHJ","schema_version":"1.0","canonical_sha256":"96464cb0e9b7ed0e58421817c28d07c8c2ca360c253e29f7ba44bc2835eb01a6","source":{"kind":"arxiv","id":"2602.16902","version":4},"attestation_state":"computed","paper":{"title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ilija Bogunovic, Juliusz Ziomek, Lorenz Wolf, Shyam Sundhar Ramesh, William Bankes, Xiaohang Tang","submitted_at":"2026-02-18T21:33:59Z","abstract_excerpt":"We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from a given source, requiring look-ahead planning and the ability to reason about how concepts are connected in the real world. We evaluate a broad set of open- and closed-source models, including Gemini-3, GPT-5, and Claude Opus 4.5, which achieve the strongest results on the easy level of the task and demonstrate superhuman performance. Despite this, performan"},"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":"2602.16902","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-18T21:33:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"488149a5c5e7053d3acc6b5fded0803a333742ee5aff1001b9e03625616df387","abstract_canon_sha256":"48f51d3eb97548595d159b22e415adc76ad470930d992088446744f77ff61d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:43.800952Z","signature_b64":"N5R45SOjFy6KbVMrBoI8HvgmCuw1t6f0/iONJOjq+p2b3wHuP096j3FVAoHq/96gf+KcswCrGW6bfG3HyVfFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96464cb0e9b7ed0e58421817c28d07c8c2ca360c253e29f7ba44bc2835eb01a6","last_reissued_at":"2026-06-02T01:03:43.800461Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:43.800461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ilija Bogunovic, Juliusz Ziomek, Lorenz Wolf, Shyam Sundhar Ramesh, William Bankes, Xiaohang Tang","submitted_at":"2026-02-18T21:33:59Z","abstract_excerpt":"We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from a given source, requiring look-ahead planning and the ability to reason about how concepts are connected in the real world. We evaluate a broad set of open- and closed-source models, including Gemini-3, GPT-5, and Claude Opus 4.5, which achieve the strongest results on the easy level of the task and demonstrate superhuman performance. Despite this, performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16902","kind":"arxiv","version":4},"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/2602.16902/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":"2602.16902","created_at":"2026-06-02T01:03:43.800521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16902v4","created_at":"2026-06-02T01:03:43.800521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16902","created_at":"2026-06-02T01:03:43.800521+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZDEZMHJW7WQ","created_at":"2026-06-02T01:03:43.800521+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZDEZMHJW7WQ4WCC","created_at":"2026-06-02T01:03:43.800521+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZDEZMHJ","created_at":"2026-06-02T01:03:43.800521+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/SZDEZMHJW7WQ4WCCDAL4FDIHZD","json":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD.json","graph_json":"https://pith.science/api/pith-number/SZDEZMHJW7WQ4WCCDAL4FDIHZD/graph.json","events_json":"https://pith.science/api/pith-number/SZDEZMHJW7WQ4WCCDAL4FDIHZD/events.json","paper":"https://pith.science/paper/SZDEZMHJ"},"agent_actions":{"view_html":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD","download_json":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD.json","view_paper":"https://pith.science/paper/SZDEZMHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16902&json=true","fetch_graph":"https://pith.science/api/pith-number/SZDEZMHJW7WQ4WCCDAL4FDIHZD/graph.json","fetch_events":"https://pith.science/api/pith-number/SZDEZMHJW7WQ4WCCDAL4FDIHZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD/action/storage_attestation","attest_author":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD/action/author_attestation","sign_citation":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD/action/citation_signature","submit_replication":"https://pith.science/pith/SZDEZMHJW7WQ4WCCDAL4FDIHZD/action/replication_record"}},"created_at":"2026-06-02T01:03:43.800521+00:00","updated_at":"2026-06-02T01:03:43.800521+00:00"}