{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQTACAJENBPD3SRN4XWVBYIHBA","short_pith_number":"pith:RQTACAJE","schema_version":"1.0","canonical_sha256":"8c26010124685e3dca2de5ed50e107082c2b6179c27d329356d9f2a1f1038622","source":{"kind":"arxiv","id":"2505.22430","version":1},"attestation_state":"computed","paper":{"title":"RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu, Yunxiang Li","submitted_at":"2025-05-28T14:55:33Z","abstract_excerpt":"Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directly prompting resource-intensive models with complex multi-stage prompts, underutilizing models' reasoning capabilities and introducing significant computational cost. In this paper, we present RAG-Zeval (RAG-Zero Evaluator), a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task. Our approach trains evaluators with reinforcement learning, facilitating compa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.22430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T14:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"bf5a5c79f1eda8e5a59376c5e2017376dcef9d1aa006d5e457cee12ff0d39709","abstract_canon_sha256":"4ca059b72b7dfcaef55e21edfab29f97115aadf7438e1aa18880c8cb77ca637f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:23.930183Z","signature_b64":"gFf9cFHXeR3s9yJP/guvBExR2T7I+Ic5A986b295XIVoY6p1XNNM3RZ4j5JZnF7tJtwK+cTJfIepWow22PN+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c26010124685e3dca2de5ed50e107082c2b6179c27d329356d9f2a1f1038622","last_reissued_at":"2026-07-05T11:11:23.929651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:23.929651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu, Yunxiang Li","submitted_at":"2025-05-28T14:55:33Z","abstract_excerpt":"Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directly prompting resource-intensive models with complex multi-stage prompts, underutilizing models' reasoning capabilities and introducing significant computational cost. In this paper, we present RAG-Zeval (RAG-Zero Evaluator), a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task. Our approach trains evaluators with reinforcement learning, facilitating compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22430","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.22430/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.22430","created_at":"2026-07-05T11:11:23.929725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22430v1","created_at":"2026-07-05T11:11:23.929725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22430","created_at":"2026-07-05T11:11:23.929725+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQTACAJENBPD","created_at":"2026-07-05T11:11:23.929725+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQTACAJENBPD3SRN","created_at":"2026-07-05T11:11:23.929725+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQTACAJE","created_at":"2026-07-05T11:11:23.929725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA","json":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA.json","graph_json":"https://pith.science/api/pith-number/RQTACAJENBPD3SRN4XWVBYIHBA/graph.json","events_json":"https://pith.science/api/pith-number/RQTACAJENBPD3SRN4XWVBYIHBA/events.json","paper":"https://pith.science/paper/RQTACAJE"},"agent_actions":{"view_html":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA","download_json":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA.json","view_paper":"https://pith.science/paper/RQTACAJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22430&json=true","fetch_graph":"https://pith.science/api/pith-number/RQTACAJENBPD3SRN4XWVBYIHBA/graph.json","fetch_events":"https://pith.science/api/pith-number/RQTACAJENBPD3SRN4XWVBYIHBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA/action/storage_attestation","attest_author":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA/action/author_attestation","sign_citation":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA/action/citation_signature","submit_replication":"https://pith.science/pith/RQTACAJENBPD3SRN4XWVBYIHBA/action/replication_record"}},"created_at":"2026-07-05T11:11:23.929725+00:00","updated_at":"2026-07-05T11:11:23.929725+00:00"}