{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBQFGVRISQNDBHTTFDXGONHDYX","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":"f536445f6b482a0a81d4d63e3c50d4c1f92075bd58c40310a813e2a72d49d3d8","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T15:39:32Z","title_canon_sha256":"23691a03083ee3b7f6799fec4fe9535ded7284cbe0c7a8fba719ffb65f12d409"},"schema_version":"1.0","source":{"id":"2409.06595","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06595","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06595v3","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06595","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"EBQFGVRISQND","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"EBQFGVRISQNDBHTT","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"EBQFGVRI","created_at":"2026-07-05T10:07:27Z"}],"graph_snapshots":[{"event_id":"sha256:d7568d00ed32c872a6772682ea33ce7dfbb469ebe23b91da857811e386248da2","target":"graph","created_at":"2026-07-05T10:07:27Z","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/2409.06595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a common paradigm to use Large Language Models (LLMs) alongside private and up-to-date knowledge bases. In this work, we address the challenges of using LLM-as-a-Judge when evaluating grounded answers generated by RAG systems. To assess the calibration and discrimination capabilities of judge models, we identify 7 generator failure modes and introduce GroUSE (Grounded QA Unitary Scoring of Evaluators), a meta-evaluation benchmark of 144 unit tests. This benchmark reveals that existing automated RAG evaluation frameworks often overlook importa","authors_text":"Ant\\'onio Loison, Bilel Omrani, Gautier Viaud, Sacha Muller","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T15:39:32Z","title":"GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06595","kind":"arxiv","version":3},"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":"sha256:00629c7782123f5aca53ab6003ebb91456eb331366e7bb866a262516bb194a2c","target":"record","created_at":"2026-07-05T10:07:27Z","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":"f536445f6b482a0a81d4d63e3c50d4c1f92075bd58c40310a813e2a72d49d3d8","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T15:39:32Z","title_canon_sha256":"23691a03083ee3b7f6799fec4fe9535ded7284cbe0c7a8fba719ffb65f12d409"},"schema_version":"1.0","source":{"id":"2409.06595","kind":"arxiv","version":3}},"canonical_sha256":"2060535628941a309e7328ee6734e3c5f8223af74722524b00de52279c64642b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2060535628941a309e7328ee6734e3c5f8223af74722524b00de52279c64642b","first_computed_at":"2026-07-05T10:07:27.040870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:27.040870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oaeSu70ivxt3osAApQhZ31X3p7T0+NZOh3NLto1Oj7zldT57hr0DkSI5ThqM7t/2H4QsrHbEmHGXZ7T4KkEzAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:27.041327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06595","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00629c7782123f5aca53ab6003ebb91456eb331366e7bb866a262516bb194a2c","sha256:d7568d00ed32c872a6772682ea33ce7dfbb469ebe23b91da857811e386248da2"],"state_sha256":"e4c37b6daf5722e966c251bba2f2f25a11c18d95b33439bc2c399b2236b9e12b"}