{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DB4M4BMDYCAMJT5LBSFAVF6NY4","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":"ff6f5b353de46145340b743029b41fc47987fd2f9f6b97c5d280dc55d9b92ed7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T00:02:05Z","title_canon_sha256":"ff47eab1bd9bf2de6ce413bfa67d870df515125a32ccde57dca35dd71b40acc3"},"schema_version":"1.0","source":{"id":"2505.13498","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13498","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13498v1","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13498","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"DB4M4BMDYCAM","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"DB4M4BMDYCAMJT5L","created_at":"2026-07-05T11:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"DB4M4BMD","created_at":"2026-07-05T11:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:e2dbdeb6e14a34b54dbe000cdc28c961ed3853e8b3abf84fabcedfa98f675273","target":"graph","created_at":"2026-07-05T11:05:46Z","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/2505.13498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated promising knowledge and reasoning abilities, yet their performance in multilingual and low-resource settings remains underexplored. Existing benchmarks often exhibit cultural bias, restrict evaluation to text-only, rely on multiple-choice formats, and, more importantly, are limited for extremely low-resource languages. To address these gaps, we introduce IRLBench, presented in parallel English and Irish, which is considered definitely endangered by UNESCO. Our benchmark consists of 12 representative subjects developed from the 2","authors_text":"Barry O'Sullivan, Hoang D. Nguyen, Khanh-Tung Tran","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T00:02:05Z","title":"IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13498","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":"sha256:2b679a28f75744b79bd2c641ce4ef3510b47b991ae18c381a652ae034241d379","target":"record","created_at":"2026-07-05T11:05:46Z","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":"ff6f5b353de46145340b743029b41fc47987fd2f9f6b97c5d280dc55d9b92ed7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T00:02:05Z","title_canon_sha256":"ff47eab1bd9bf2de6ce413bfa67d870df515125a32ccde57dca35dd71b40acc3"},"schema_version":"1.0","source":{"id":"2505.13498","kind":"arxiv","version":1}},"canonical_sha256":"1878ce0583c080c4cfab0c8a0a97cdc715c44c26e51e154704b60a39d4913a39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1878ce0583c080c4cfab0c8a0a97cdc715c44c26e51e154704b60a39d4913a39","first_computed_at":"2026-07-05T11:05:46.869566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:46.869566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+1+c3AGlUH+HVWNTshq6UpiY76l54zUrDXMmMUGN2K2Z0lyPCVfzrjuCt9qkghY3ISIlE7WUdauF8cgBKDz8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:46.869951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13498","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b679a28f75744b79bd2c641ce4ef3510b47b991ae18c381a652ae034241d379","sha256:e2dbdeb6e14a34b54dbe000cdc28c961ed3853e8b3abf84fabcedfa98f675273"],"state_sha256":"24b5899be734c7e89721a430fe1ec53901a68dd337eaff885e5aeeb14e0cf13e"}