{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7KMGZOHPLKDR75V3Q4NIA75MPO","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":"045f54cb83edd1e16149a0a4e9f2e8239908851504d6211c0e30dc1081034584","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T11:00:38Z","title_canon_sha256":"6eaa4e38528abbbe348d78d58346893f74d3548685484478677a4689007ba918"},"schema_version":"1.0","source":{"id":"2406.15053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15053","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15053v2","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15053","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"7KMGZOHPLKDR","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"7KMGZOHPLKDR75V3","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"7KMGZOHP","created_at":"2026-07-05T09:22:19Z"}],"graph_snapshots":[{"event_id":"sha256:a4b0393746f543a8df30e07a171c265db8cdbb5f68e6ec88ec8fdad3b9a91bb4","target":"graph","created_at":"2026-07-05T09:22:19Z","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/2406.15053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation of multilingual Large Language Models (LLMs) is challenging due to a variety of factors -- the lack of benchmarks with sufficient linguistic diversity, contamination of popular benchmarks into LLM pre-training data and the lack of local, cultural nuances in translated benchmarks. In this work, we study human and LLM-based evaluation in a multilingual, multi-cultural setting. We evaluate 30 models across 10 Indic languages by conducting 90K human evaluations and 30K LLM-based evaluations and find that models such as GPT-4o and Llama-3 70B consistently perform best for most Indic lang","authors_text":"Aditya Yadavalli, Ishaan Watts, Manohar Swaminathan, Sunayana Sitaram, Varun Gumma, Vivek Seshadri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T11:00:38Z","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15053","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:e7a25682bdf6addc09e46a90cb42a70144df753a96f0af7a9c92b840290031ba","target":"record","created_at":"2026-07-05T09:22:19Z","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":"045f54cb83edd1e16149a0a4e9f2e8239908851504d6211c0e30dc1081034584","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T11:00:38Z","title_canon_sha256":"6eaa4e38528abbbe348d78d58346893f74d3548685484478677a4689007ba918"},"schema_version":"1.0","source":{"id":"2406.15053","kind":"arxiv","version":2}},"canonical_sha256":"fa986cb8ef5a871ff6bb871a807fac7ba7bebb2e4c45bab832e7ba3f7fb6921a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa986cb8ef5a871ff6bb871a807fac7ba7bebb2e4c45bab832e7ba3f7fb6921a","first_computed_at":"2026-07-05T09:22:19.923509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:19.923509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oSn20D6lakY+LETlc0GqjmzpDmc1+wOVTTzDW5iOgx1++nBjsXf8h7NwYndSU+AXMNCzhfV0PdrbJL+7F7KtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:19.924097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7a25682bdf6addc09e46a90cb42a70144df753a96f0af7a9c92b840290031ba","sha256:a4b0393746f543a8df30e07a171c265db8cdbb5f68e6ec88ec8fdad3b9a91bb4"],"state_sha256":"1231f5e7101c305303b36e1167690ad62bd76a29faa8d39b99e7c279fb5a976d"}