{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WXYEM7LXLH4WREDO2TJ7QBAYP3","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":"3da409a113fda626aff7e7180ffb5fa9e0294edc85f5315b7a80492213fba518","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:59:49Z","title_canon_sha256":"cacd33c482e6e0914bfe33648617b39400b6058f948f6ae81cb8d0e83196c289"},"schema_version":"1.0","source":{"id":"2406.11681","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11681","created_at":"2026-07-05T08:32:56Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11681v1","created_at":"2026-07-05T08:32:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11681","created_at":"2026-07-05T08:32:56Z"},{"alias_kind":"pith_short_12","alias_value":"WXYEM7LXLH4W","created_at":"2026-07-05T08:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"WXYEM7LXLH4WREDO","created_at":"2026-07-05T08:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"WXYEM7LX","created_at":"2026-07-05T08:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:3cffc400c8ce9dfb574d16c10336a81f8eb06880f739c2b190c9c43d35cdf0d2","target":"graph","created_at":"2026-07-05T08:32:56Z","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/2406.11681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved remarkable success on general NLP tasks, but they may fall short for domain-specific problems. Recently, various Retrieval-Augmented Large Language Models (RALLMs) are proposed to address this shortcoming. However, existing evaluation tools only provide a few baselines and evaluate them on various domains without mining the depth of domain knowledge. In this paper, we address the challenges of evaluating RALLMs by introducing the R-Eval toolkit, a Python toolkit designed to streamline the evaluation of different RAG workflows in conjunction with LLMs. Our to","authors_text":"Jifan Yu, Jing Zhang, Juanzi Li, Lei Hou, Shangqing Tu, Xiaozhi Wang, Yaran Shi, Yuanchun Wang, Yuyang Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:59:49Z","title":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11681","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":"sha256:8ebce8da49e7a52c99f643a31cb3dd5ab4926e8e7e182c93379f58a5081f0965","target":"record","created_at":"2026-07-05T08:32:56Z","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":"3da409a113fda626aff7e7180ffb5fa9e0294edc85f5315b7a80492213fba518","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:59:49Z","title_canon_sha256":"cacd33c482e6e0914bfe33648617b39400b6058f948f6ae81cb8d0e83196c289"},"schema_version":"1.0","source":{"id":"2406.11681","kind":"arxiv","version":1}},"canonical_sha256":"b5f0467d7759f968906ed4d3f804187ed3063ea6142a2660ea75f3ba818ea6b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5f0467d7759f968906ed4d3f804187ed3063ea6142a2660ea75f3ba818ea6b0","first_computed_at":"2026-07-05T08:32:56.237037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:56.237037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"liOJO5i6oJWkVb0pePyhK7a4uskVbWpOHQBk1ycLvVgqEeAkdw2wXhnbZWg45+D1K2JcvUoPxPqfEaW5hn8hCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:56.237548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11681","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ebce8da49e7a52c99f643a31cb3dd5ab4926e8e7e182c93379f58a5081f0965","sha256:3cffc400c8ce9dfb574d16c10336a81f8eb06880f739c2b190c9c43d35cdf0d2"],"state_sha256":"6935f1d00dfac68e129bb6c9926b8b75c3e1cce15d78693ad46b36f17a65baff"}