{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XPUE2RQTCXLDIV2UJDJIIQ2VRD","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":"10647c81fd5b19d857a6c067f4d128b14c1e218a9161b478aba2f2ded74b989e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:14:11Z","title_canon_sha256":"d163a1e0ff3ec59b2c70745c05911e1e4aa4550482b38f3af943f103b25348fa"},"schema_version":"1.0","source":{"id":"2405.13622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13622","created_at":"2026-07-05T08:22:05Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13622v1","created_at":"2026-07-05T08:22:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13622","created_at":"2026-07-05T08:22:05Z"},{"alias_kind":"pith_short_12","alias_value":"XPUE2RQTCXLD","created_at":"2026-07-05T08:22:05Z"},{"alias_kind":"pith_short_16","alias_value":"XPUE2RQTCXLDIV2U","created_at":"2026-07-05T08:22:05Z"},{"alias_kind":"pith_short_8","alias_value":"XPUE2RQT","created_at":"2026-07-05T08:22:05Z"}],"graph_snapshots":[{"event_id":"sha256:14e78e38670df57a577e71a835ac856d56d8c4acee5a11e19f7cabb632111d8d","target":"graph","created_at":"2026-07-05T08:22:05Z","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/2405.13622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions based on the corpus of documents associated with the task. Our method is an automated, cost-efficient, interpretable, and robust strategy to select the optimal components for a RAG system. We leverage Item Response Theory (IRT) to estimate the quality of an exam and its informativeness on task-specific accuracy. IRT also provides a natural way to iteratively","authors_text":"Anoop Deoras, Behrooz Omidvar-Tehrani, Gauthier Guinet, Laurent Callot","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:14:11Z","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13622","kind":"arxiv","version":1},"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:b19edca717804c484c1974bd849cc4ef06a711cd6bda3fc430708c450b4495ff","target":"record","created_at":"2026-07-05T08:22:05Z","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":"10647c81fd5b19d857a6c067f4d128b14c1e218a9161b478aba2f2ded74b989e","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:14:11Z","title_canon_sha256":"d163a1e0ff3ec59b2c70745c05911e1e4aa4550482b38f3af943f103b25348fa"},"schema_version":"1.0","source":{"id":"2405.13622","kind":"arxiv","version":1}},"canonical_sha256":"bbe84d461315d634575448d284435588eb9498826a9abd4f33437bde51d514e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbe84d461315d634575448d284435588eb9498826a9abd4f33437bde51d514e8","first_computed_at":"2026-07-05T08:22:05.176139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:05.176139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gg8IqVptuS7Ms7YFYTd2sup1WtlrDhmcVedXdBOhhIGqXGWFdxBXyVF+hchww5nsRms/80+mQBhhsMVhNYdzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:05.176620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b19edca717804c484c1974bd849cc4ef06a711cd6bda3fc430708c450b4495ff","sha256:14e78e38670df57a577e71a835ac856d56d8c4acee5a11e19f7cabb632111d8d"],"state_sha256":"bb769e40667087660d3c00f0ec3b85b75c8773fd263be654fce4ffc4a047652b"}