{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LR7DZBKRBVJ5JY2OKQNVOJOFXD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"960e7b36473334bbab74d8e8cbefed83570648a54d4d751033f6e089c9a7785c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T11:50:29Z","title_canon_sha256":"33258fdb6bf3d67ff4cbe0f64de7b5df90cc0835c5c494aa518ae2d6576d7d1f"},"schema_version":"1.0","source":{"id":"2406.06196","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06196","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06196v3","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06196","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"LR7DZBKRBVJ5","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"LR7DZBKRBVJ5JY2O","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"LR7DZBKR","created_at":"2026-07-05T09:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:76c65b18c2bcad47d967d13017489c166d08c02e76eb041376cd4c367fc698c7","target":"graph","created_at":"2026-07-05T09:28:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.06196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrew M. Bean, Ethan A. Chi, Hannah Rose Kirk, Harry Mayne, Jabez Magomere, Ryan Chi, Scott A. Hale, Simi Hellsten","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T11:50:29Z","title":"LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06196","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f65b62f8c7ed8af44540b6263420088d8e4c59fec608ac14659cc85d3a2ad4f7","target":"record","created_at":"2026-07-05T09:28:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"960e7b36473334bbab74d8e8cbefed83570648a54d4d751033f6e089c9a7785c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T11:50:29Z","title_canon_sha256":"33258fdb6bf3d67ff4cbe0f64de7b5df90cc0835c5c494aa518ae2d6576d7d1f"},"schema_version":"1.0","source":{"id":"2406.06196","kind":"arxiv","version":3}},"canonical_sha256":"5c7e3c85510d53d4e34e541b5725c5b8f6f62c21a8eef9941e16ab4d38f2cfb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7e3c85510d53d4e34e541b5725c5b8f6f62c21a8eef9941e16ab4d38f2cfb1","first_computed_at":"2026-07-05T09:28:51.070171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:51.070171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nkNLgR8OvZyFiWdJdW2CVv+9ojVpZLEHTdojvSR6KCUPzZYpm72Mxeuoi56r2tTtpzut46GZfu5ECw4n6RQYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:51.070598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06196","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f65b62f8c7ed8af44540b6263420088d8e4c59fec608ac14659cc85d3a2ad4f7","sha256:76c65b18c2bcad47d967d13017489c166d08c02e76eb041376cd4c367fc698c7"],"state_sha256":"307a914a1836008e70bcac2df987a6a1589aad1adf36abd6aef31220d807fc3b"}