{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R4OL3ADHFFBCEQZDWLCI3UYNSZ","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":"37a51eb55e301b2e0cb5adfd5e17668426b95ab58ecbb8e83b4354867c2e0e78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T23:05:46Z","title_canon_sha256":"635d5e53c6dc4e5c11052e3438ba7849f693cca0a03dfa8a5ab53451e2acf006"},"schema_version":"1.0","source":{"id":"2504.17137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17137","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17137v1","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17137","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"R4OL3ADHFFBC","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"R4OL3ADHFFBCEQZD","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"R4OL3ADH","created_at":"2026-07-05T10:53:22Z"}],"graph_snapshots":[{"event_id":"sha256:2a19e988364ad275708a43245f881cb0f44148a56f28c91f41068fe1a2441afc","target":"graph","created_at":"2026-07-05T10:53:22Z","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/2504.17137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has gained prominence as an effective method for enhancing the generative capabilities of Large Language Models (LLMs) through the incorporation of external knowledge. However, the evaluation of RAG systems remains a challenge, due to the intricate interplay between retrieval and generation components. This limitation has resulted in a scarcity of benchmarks that facilitate a detailed, component-specific assessment. In this work, we present MIRAGE, a Question Answering dataset specifically designed for RAG evaluation. MIRAGE consists of 7,560 curated instan","authors_text":"Chanhee Park, Chanjun Park, Heuiseok Lim, Hyeonseok Moon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T23:05:46Z","title":"MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17137","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":"sha256:3182b58404d36aec597df4a9fec2d1edf113e8557b3810104303a9345ba8e1fb","target":"record","created_at":"2026-07-05T10:53:22Z","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":"37a51eb55e301b2e0cb5adfd5e17668426b95ab58ecbb8e83b4354867c2e0e78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T23:05:46Z","title_canon_sha256":"635d5e53c6dc4e5c11052e3438ba7849f693cca0a03dfa8a5ab53451e2acf006"},"schema_version":"1.0","source":{"id":"2504.17137","kind":"arxiv","version":1}},"canonical_sha256":"8f1cbd80672942224323b2c48dd30d964f07a142e4744bff765e156114a07679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f1cbd80672942224323b2c48dd30d964f07a142e4744bff765e156114a07679","first_computed_at":"2026-07-05T10:53:22.956866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:22.956866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oTfw6mzHy3v6++LCQF8LSfrXzPGIcwn2oMKyTUMU7DBWuqmOg56ZbfCtxYy01hSWHy36kOVdabjf8CyxBJvUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:22.957390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3182b58404d36aec597df4a9fec2d1edf113e8557b3810104303a9345ba8e1fb","sha256:2a19e988364ad275708a43245f881cb0f44148a56f28c91f41068fe1a2441afc"],"state_sha256":"a6e87531c3687a148421ee0950f345a9643eb3c33e7e07966f14c57b056236f9"}