{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E56CR3MBOJMNUIORPCLKPT5ROP","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":"1dc9000f857f61320dfc2e695b5685d67bbf2b51a801e61ac0ba69aa0f72bfc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T06:53:28Z","title_canon_sha256":"e95af81686fc3ec6152fca22b3efa83ed010236b5e56b2006892477eb05b13f5"},"schema_version":"1.0","source":{"id":"2508.11260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11260","created_at":"2026-07-05T11:54:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11260v1","created_at":"2026-07-05T11:54:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11260","created_at":"2026-07-05T11:54:21Z"},{"alias_kind":"pith_short_12","alias_value":"E56CR3MBOJMN","created_at":"2026-07-05T11:54:21Z"},{"alias_kind":"pith_short_16","alias_value":"E56CR3MBOJMNUIOR","created_at":"2026-07-05T11:54:21Z"},{"alias_kind":"pith_short_8","alias_value":"E56CR3MB","created_at":"2026-07-05T11:54:21Z"}],"graph_snapshots":[{"event_id":"sha256:fb3c11c6a55f3023da120ac934340ca9df12e3fb394cec45dc9df2b659de0b6d","target":"graph","created_at":"2026-07-05T11:54:21Z","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/2508.11260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated potential in reasoning tasks, but their performance on linguistics puzzles remains consistently poor. These puzzles, often derived from Linguistics Olympiad (LO) contests, provide a minimal contamination environment to assess LLMs' linguistic reasoning abilities across low-resource languages. This work analyses LLMs' performance on 629 problems across 41 low-resource languages by labelling each with linguistically informed features to unveil weaknesses. Our analyses show that LLMs struggle with puzzles involving higher morphological complexity and","authors_text":"Antara Raaghavi Bhattacharya, Dang Khoa Dang Dinh, Daria Kotova, Ekaterina Kochmar, Gaurja Aeron, Ikhlasul Akmal Hanif, KV Aditya Srivatsa, Monojit Choudhury, Mukund Choudhary","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T06:53:28Z","title":"UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11260","kind":"arxiv","version":1},"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:efd5501417b2507dfd58a28733af674f24002b4b3a7e045e2389b842e2ef863a","target":"record","created_at":"2026-07-05T11:54:21Z","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":"1dc9000f857f61320dfc2e695b5685d67bbf2b51a801e61ac0ba69aa0f72bfc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T06:53:28Z","title_canon_sha256":"e95af81686fc3ec6152fca22b3efa83ed010236b5e56b2006892477eb05b13f5"},"schema_version":"1.0","source":{"id":"2508.11260","kind":"arxiv","version":1}},"canonical_sha256":"277c28ed817258da21d17896a7cfb173d6ec34357ac0a5d9d796d96e5c72ee87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"277c28ed817258da21d17896a7cfb173d6ec34357ac0a5d9d796d96e5c72ee87","first_computed_at":"2026-07-05T11:54:21.635204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:21.635204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cptw6l7Fcw9igZBRW57cF+ZYP2RcitciVcEhAOWSU3CM66dHx6KPMZPFSkQ5Fy6/Ludx5vSc5x/IIfZ5RLlnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:21.635635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efd5501417b2507dfd58a28733af674f24002b4b3a7e045e2389b842e2ef863a","sha256:fb3c11c6a55f3023da120ac934340ca9df12e3fb394cec45dc9df2b659de0b6d"],"state_sha256":"4d3b61ca43dcca5a2defc3783a3d9c7854a8aab49ee3b2b0dd95034ef9313667"}