{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X7ADFAMJDJYDFOUCE44BYL5A52","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":"7091e2d700190584356f0d5dbc19871bcf21226c9b1e3bb4eb8e99725df4ee70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T21:30:03Z","title_canon_sha256":"db06f538ca623b2dd6c65f5d3f8c67b9e759b013c5cf36731392afad970c1780"},"schema_version":"1.0","source":{"id":"2501.09164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09164","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09164v1","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09164","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"X7ADFAMJDJYD","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"X7ADFAMJDJYDFOUC","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"X7ADFAMJ","created_at":"2026-07-05T10:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:6a3615cbfd1ad0daf038a6b3d28477fa0dc5cff5bb3b26800b1fc55925eaf4ee","target":"graph","created_at":"2026-07-05T10:01:42Z","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/2501.09164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we address the challenge of evaluating large language models (LLMs) on the short answer matching task for Latvian and Lithuanian languages. We introduce novel datasets consisting of 502 Latvian and 690 Lithuanian question-answer pairs. For each question-answer pair, we generated matched and non-matched answers using a set of alteration rules specifically designed to introduce small but meaningful changes in the text. These generated answers serve as test cases to assess the ability of LLMs to detect subtle differences in matching of the original answers. A subset of the datasets ","authors_text":"Artur Kiulian, {\\L}ukasz Gaga{\\l}a, Oxana Vitman, Yevhen Kostiuk","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T21:30:03Z","title":"The Veln(ia)s is in the Details: Evaluating LLM Judgment on Latvian and Lithuanian Short Answer Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09164","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":"sha256:176366de0521f6e7857a767f3cff2cef95f5212f5241ddd122a8ac78efc738f2","target":"record","created_at":"2026-07-05T10:01:42Z","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":"7091e2d700190584356f0d5dbc19871bcf21226c9b1e3bb4eb8e99725df4ee70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T21:30:03Z","title_canon_sha256":"db06f538ca623b2dd6c65f5d3f8c67b9e759b013c5cf36731392afad970c1780"},"schema_version":"1.0","source":{"id":"2501.09164","kind":"arxiv","version":1}},"canonical_sha256":"bfc03281891a7032ba8227381c2fa0ee9eda45c721c039fc2f5746ed1a73706c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc03281891a7032ba8227381c2fa0ee9eda45c721c039fc2f5746ed1a73706c","first_computed_at":"2026-07-05T10:01:42.872941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:42.872941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WuTgawcIZiHY63M6mnhRR9mVWNx9Y3ysIE3ZykyoCip+J2R5mRVokdUFB/ft4MTDd6aVcOA+IQK73hkYNq4fBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:42.873447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09164","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:176366de0521f6e7857a767f3cff2cef95f5212f5241ddd122a8ac78efc738f2","sha256:6a3615cbfd1ad0daf038a6b3d28477fa0dc5cff5bb3b26800b1fc55925eaf4ee"],"state_sha256":"9aa9e79e8e5b448308eab48f3b0eef5bfde268a0de3da75a7b1a7153a886286d"}