{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BVYY4DEACGIKS3H5Z2J6AXUNSI","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":"0e31928765cc8d982512762caebe0ec1a18f0e4548d94a7d5e24f759182bd0fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T09:45:32Z","title_canon_sha256":"be6f4eff02942de6e4262522382268a17c16ffb8d2596c3d9e1f24ca32cd892c"},"schema_version":"1.0","source":{"id":"2410.13394","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13394","created_at":"2026-07-05T11:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13394v2","created_at":"2026-07-05T11:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13394","created_at":"2026-07-05T11:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"BVYY4DEACGIK","created_at":"2026-07-05T11:39:05Z"},{"alias_kind":"pith_short_16","alias_value":"BVYY4DEACGIKS3H5","created_at":"2026-07-05T11:39:05Z"},{"alias_kind":"pith_short_8","alias_value":"BVYY4DEA","created_at":"2026-07-05T11:39:05Z"}],"graph_snapshots":[{"event_id":"sha256:87b7b99dcb570100df2db13e197be678976dc55e12a79d09de69a9db8f2eea26","target":"graph","created_at":"2026-07-05T11:39:05Z","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/2410.13394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on English, revealing a significant gap in multilingual evaluation frameworks. We introduce the Cross Lingual Auto Evaluation (CIA) Suite, an extensible framework that includes evaluator LLMs (Hercule) and a novel test set (Recon) specifically designed for multilingual evaluation. Our test set features 500 human-annotated instructions spanning various task capabilitie","authors_text":"Anoop Kunchukuttan, Dilip Venkatesh, Mitesh M. Khapra, Mohammed Safi Ur Rahman Khan, Raj Dabre, Sumanth Doddapaneni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T09:45:32Z","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13394","kind":"arxiv","version":2},"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:bd60b58d5e985fb9652c24e7297f0df621cef21be6550557766bf05d7bbd63f7","target":"record","created_at":"2026-07-05T11:39:05Z","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":"0e31928765cc8d982512762caebe0ec1a18f0e4548d94a7d5e24f759182bd0fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T09:45:32Z","title_canon_sha256":"be6f4eff02942de6e4262522382268a17c16ffb8d2596c3d9e1f24ca32cd892c"},"schema_version":"1.0","source":{"id":"2410.13394","kind":"arxiv","version":2}},"canonical_sha256":"0d718e0c801190a96cfdce93e05e8d92362c541f1869af7390cf9f460b3f9217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d718e0c801190a96cfdce93e05e8d92362c541f1869af7390cf9f460b3f9217","first_computed_at":"2026-07-05T11:39:05.005009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:05.005009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAuP+l1qcIPTbrGJKvcCXtKC6oxInVk8v2RbXNbyDwywdUfgKolLYdxXyL5ZYEoYPqhle3MB8skwU1e9DYCSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:05.005477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13394","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd60b58d5e985fb9652c24e7297f0df621cef21be6550557766bf05d7bbd63f7","sha256:87b7b99dcb570100df2db13e197be678976dc55e12a79d09de69a9db8f2eea26"],"state_sha256":"e9bd8d017e4183aa29b8d9467d09fbb2b83e19c113235f8cfa806de9677c058c"}