{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RQTACAJENBPD3SRN4XWVBYIHBA","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":"4ca059b72b7dfcaef55e21edfab29f97115aadf7438e1aa18880c8cb77ca637f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T14:55:33Z","title_canon_sha256":"bf5a5c79f1eda8e5a59376c5e2017376dcef9d1aa006d5e457cee12ff0d39709"},"schema_version":"1.0","source":{"id":"2505.22430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22430","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22430v1","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22430","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"RQTACAJENBPD","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"RQTACAJENBPD3SRN","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"RQTACAJE","created_at":"2026-07-05T11:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:b7d80cd7bd24ce1fa19aa94e781f27ecac7f8a49349401783a0f403600848970","target":"graph","created_at":"2026-07-05T11:11:23Z","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/2505.22430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu, Yunxiang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T14:55:33Z","title":"RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22430","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":"sha256:94beb3e7d3a1467f88b834c84fa8f34b6e8e3a12bf0bccc5d970dfb969dbf868","target":"record","created_at":"2026-07-05T11:11:23Z","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":"4ca059b72b7dfcaef55e21edfab29f97115aadf7438e1aa18880c8cb77ca637f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T14:55:33Z","title_canon_sha256":"bf5a5c79f1eda8e5a59376c5e2017376dcef9d1aa006d5e457cee12ff0d39709"},"schema_version":"1.0","source":{"id":"2505.22430","kind":"arxiv","version":1}},"canonical_sha256":"8c26010124685e3dca2de5ed50e107082c2b6179c27d329356d9f2a1f1038622","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c26010124685e3dca2de5ed50e107082c2b6179c27d329356d9f2a1f1038622","first_computed_at":"2026-07-05T11:11:23.929651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:23.929651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFf9cFHXeR3s9yJP/guvBExR2T7I+Ic5A986b295XIVoY6p1XNNM3RZ4j5JZnF7tJtwK+cTJfIepWow22PN+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:23.930183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94beb3e7d3a1467f88b834c84fa8f34b6e8e3a12bf0bccc5d970dfb969dbf868","sha256:b7d80cd7bd24ce1fa19aa94e781f27ecac7f8a49349401783a0f403600848970"],"state_sha256":"3db80a7af8612c5822ad2af9b14808baf6fe446226093f62e78ff830bbfa5a67"}