{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BVYY4DEACGIKS3H5Z2J6AXUNSI","short_pith_number":"pith:BVYY4DEA","schema_version":"1.0","canonical_sha256":"0d718e0c801190a96cfdce93e05e8d92362c541f1869af7390cf9f460b3f9217","source":{"kind":"arxiv","id":"2410.13394","version":2},"attestation_state":"computed","paper":{"title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Dilip Venkatesh, Mitesh M. Khapra, Mohammed Safi Ur Rahman Khan, Raj Dabre, Sumanth Doddapaneni","submitted_at":"2024-10-17T09:45:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13394","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T09:45:32Z","cross_cats_sorted":[],"title_canon_sha256":"be6f4eff02942de6e4262522382268a17c16ffb8d2596c3d9e1f24ca32cd892c","abstract_canon_sha256":"0e31928765cc8d982512762caebe0ec1a18f0e4548d94a7d5e24f759182bd0fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:05.005477Z","signature_b64":"HAuP+l1qcIPTbrGJKvcCXtKC6oxInVk8v2RbXNbyDwywdUfgKolLYdxXyL5ZYEoYPqhle3MB8skwU1e9DYCSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d718e0c801190a96cfdce93e05e8d92362c541f1869af7390cf9f460b3f9217","last_reissued_at":"2026-07-05T11:39:05.005009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:05.005009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Dilip Venkatesh, Mitesh M. Khapra, Mohammed Safi Ur Rahman Khan, Raj Dabre, Sumanth Doddapaneni","submitted_at":"2024-10-17T09:45:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13394","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13394/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.13394","created_at":"2026-07-05T11:39:05.005062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13394v2","created_at":"2026-07-05T11:39:05.005062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13394","created_at":"2026-07-05T11:39:05.005062+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVYY4DEACGIK","created_at":"2026-07-05T11:39:05.005062+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVYY4DEACGIKS3H5","created_at":"2026-07-05T11:39:05.005062+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVYY4DEA","created_at":"2026-07-05T11:39:05.005062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.10477","citing_title":"PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI","json":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI.json","graph_json":"https://pith.science/api/pith-number/BVYY4DEACGIKS3H5Z2J6AXUNSI/graph.json","events_json":"https://pith.science/api/pith-number/BVYY4DEACGIKS3H5Z2J6AXUNSI/events.json","paper":"https://pith.science/paper/BVYY4DEA"},"agent_actions":{"view_html":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI","download_json":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI.json","view_paper":"https://pith.science/paper/BVYY4DEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13394&json=true","fetch_graph":"https://pith.science/api/pith-number/BVYY4DEACGIKS3H5Z2J6AXUNSI/graph.json","fetch_events":"https://pith.science/api/pith-number/BVYY4DEACGIKS3H5Z2J6AXUNSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI/action/storage_attestation","attest_author":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI/action/author_attestation","sign_citation":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI/action/citation_signature","submit_replication":"https://pith.science/pith/BVYY4DEACGIKS3H5Z2J6AXUNSI/action/replication_record"}},"created_at":"2026-07-05T11:39:05.005062+00:00","updated_at":"2026-07-05T11:39:05.005062+00:00"}