{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LR7DZBKRBVJ5JY2OKQNVOJOFXD","short_pith_number":"pith:LR7DZBKR","schema_version":"1.0","canonical_sha256":"5c7e3c85510d53d4e34e541b5725c5b8f6f62c21a8eef9941e16ab4d38f2cfb1","source":{"kind":"arxiv","id":"2406.06196","version":3},"attestation_state":"computed","paper":{"title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew M. Bean, Ethan A. Chi, Hannah Rose Kirk, Harry Mayne, Jabez Magomere, Ryan Chi, Scott A. Hale, Simi Hellsten","submitted_at":"2024-06-10T11:50:29Z","abstract_excerpt":"In this paper, we present the LingOly benchmark, a novel benchmark for advanced reasoning abilities in large language models. Using challenging Linguistic Olympiad puzzles, we evaluate (i) capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages, and (ii) abilities to follow complex task instructions. The LingOly benchmark covers more than 90 mostly low-resource languages, minimising issues of data contamination, and contains 1,133 problems across 6 formats and 5 levels of human difficulty. We assess performance with both di"},"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":"2406.06196","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T11:50:29Z","cross_cats_sorted":[],"title_canon_sha256":"33258fdb6bf3d67ff4cbe0f64de7b5df90cc0835c5c494aa518ae2d6576d7d1f","abstract_canon_sha256":"960e7b36473334bbab74d8e8cbefed83570648a54d4d751033f6e089c9a7785c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:51.070598Z","signature_b64":"nkNLgR8OvZyFiWdJdW2CVv+9ojVpZLEHTdojvSR6KCUPzZYpm72Mxeuoi56r2tTtpzut46GZfu5ECw4n6RQYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7e3c85510d53d4e34e541b5725c5b8f6f62c21a8eef9941e16ab4d38f2cfb1","last_reissued_at":"2026-07-05T09:28:51.070171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:51.070171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew M. Bean, Ethan A. Chi, Hannah Rose Kirk, Harry Mayne, Jabez Magomere, Ryan Chi, Scott A. Hale, Simi Hellsten","submitted_at":"2024-06-10T11:50:29Z","abstract_excerpt":"In this paper, we present the LingOly benchmark, a novel benchmark for advanced reasoning abilities in large language models. Using challenging Linguistic Olympiad puzzles, we evaluate (i) capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages, and (ii) abilities to follow complex task instructions. The LingOly benchmark covers more than 90 mostly low-resource languages, minimising issues of data contamination, and contains 1,133 problems across 6 formats and 5 levels of human difficulty. We assess performance with both di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06196","kind":"arxiv","version":3},"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/2406.06196/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":"2406.06196","created_at":"2026-07-05T09:28:51.070226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06196v3","created_at":"2026-07-05T09:28:51.070226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06196","created_at":"2026-07-05T09:28:51.070226+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR7DZBKRBVJ5","created_at":"2026-07-05T09:28:51.070226+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR7DZBKRBVJ5JY2O","created_at":"2026-07-05T09:28:51.070226+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR7DZBKR","created_at":"2026-07-05T09:28:51.070226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16125","citing_title":"KoBALT: Korean Benchmark For Advanced Linguistic Tasks","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD","json":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD.json","graph_json":"https://pith.science/api/pith-number/LR7DZBKRBVJ5JY2OKQNVOJOFXD/graph.json","events_json":"https://pith.science/api/pith-number/LR7DZBKRBVJ5JY2OKQNVOJOFXD/events.json","paper":"https://pith.science/paper/LR7DZBKR"},"agent_actions":{"view_html":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD","download_json":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD.json","view_paper":"https://pith.science/paper/LR7DZBKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06196&json=true","fetch_graph":"https://pith.science/api/pith-number/LR7DZBKRBVJ5JY2OKQNVOJOFXD/graph.json","fetch_events":"https://pith.science/api/pith-number/LR7DZBKRBVJ5JY2OKQNVOJOFXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD/action/storage_attestation","attest_author":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD/action/author_attestation","sign_citation":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD/action/citation_signature","submit_replication":"https://pith.science/pith/LR7DZBKRBVJ5JY2OKQNVOJOFXD/action/replication_record"}},"created_at":"2026-07-05T09:28:51.070226+00:00","updated_at":"2026-07-05T09:28:51.070226+00:00"}