{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UQZDXALHYY6ZA25CTICEHWQKV7","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":"5935a61411c037544233ebc3427f46911244d29f2ee0456264c531272591dce5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:18:49Z","title_canon_sha256":"c73d7e36c77310ddab14c7630539736f826227241d35822db08e8ce351195b86"},"schema_version":"1.0","source":{"id":"2410.13716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13716","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13716v2","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13716","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"UQZDXALHYY6Z","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"UQZDXALHYY6ZA25C","created_at":"2026-07-05T10:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"UQZDXALH","created_at":"2026-07-05T10:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:f0cd5ae60e36bda017d31b3208eadb7612d91bcdb62af982aebf693c92db924e","target":"graph","created_at":"2026-07-05T10:41:16Z","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/2410.13716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional retrieval-augmented generation (RAG) benchmarks evaluate systems using heuristic-based metrics, but these require human preferences as the ground truth for reference. In contrast, arena-based benchmarks, where systems compete against each other, require an expensive large language model (LLM) as a judge for a reliable evaluation. We present a simple efficient technique to combine the best of both worlds. The idea is to train a surrogate judge using heuristic metrics as input, to output the LLM as a judge prediction. In our work, we develop MIRAGE-Bench, a synthetic arena-based RAG ","authors_text":"Amin Ahmad, Ge Luo, Jimmy Lin, Nandan Thakur, Suleman Kazi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:18:49Z","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13716","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":"sha256:7333f56305a369aa8c76c1f5cbda13283a0e0b34589bfe61b5a961d110bb76f7","target":"record","created_at":"2026-07-05T10:41:16Z","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":"5935a61411c037544233ebc3427f46911244d29f2ee0456264c531272591dce5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:18:49Z","title_canon_sha256":"c73d7e36c77310ddab14c7630539736f826227241d35822db08e8ce351195b86"},"schema_version":"1.0","source":{"id":"2410.13716","kind":"arxiv","version":2}},"canonical_sha256":"a4323b8167c63d906ba29a0443da0aaffcb42a818cee8ea92183e3539429be32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4323b8167c63d906ba29a0443da0aaffcb42a818cee8ea92183e3539429be32","first_computed_at":"2026-07-05T10:41:16.186103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:16.186103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CpDuK9fh9J9oGMf2D42GRYdVr764VaFNOw6+eppcS5lkbLkxgxrB9q6BgQNPiIKLVXShs+VcDw+B0m9DF6k+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:16.186622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7333f56305a369aa8c76c1f5cbda13283a0e0b34589bfe61b5a961d110bb76f7","sha256:f0cd5ae60e36bda017d31b3208eadb7612d91bcdb62af982aebf693c92db924e"],"state_sha256":"42252661bd53c0020c3c887ab578913270e21f59e9c85ee7eb4a71a83508d5c4"}