{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KJ3GLN3IMWW72RZIYRM4HPVTLB","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":"007146ebe8160da410be50d017592d232248f0d29c844a95b1aa4da35c6cb3ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T19:23:54Z","title_canon_sha256":"91b21454bfac08ab0267ff0ab7c5697b9c78babb8efb3a88d2060faa54199c57"},"schema_version":"1.0","source":{"id":"2309.15217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15217","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15217v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15217","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"KJ3GLN3IMWW7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJ3GLN3IMWW72RZI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJ3GLN3I","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8b08d53f92d32eb5af493b3d31351352b16696d08183f2c51a7afe25a61de696","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We put forward a suite of metrics which can be used to evaluate these different dimensions without having to rely on ground truth human annotations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-based judgments of context relevance, faithfulness, and answer relevance will correlate sufficiently with human judgments across domains and models without additional calibration or validation data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ragas supplies reference-free metrics for measuring context relevance, faithfulness to retrieved passages, and answer quality in RAG pipelines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines."}],"snapshot_sha256":"e8604ffb2e1165e3985ff08277d4af73b8bd189af2184a600778006a75c32a97"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a3f195451793100092dea034b102bece97ffd22a817852f739338ab1cfff9e1a"},"paper":{"abstract_excerpt":"We introduce Ragas (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation (RAG) pipelines. RAG systems are composed of a retrieval and an LLM based generation module, and provide LLMs with knowledge from a reference textual database, which enables them to act as a natural language layer between a user and textual databases, reducing the risk of hallucinations. Evaluating RAG architectures is, however, challenging because there are several dimensions to consider: the ability of the retrieval system to identify relevant and focuse","authors_text":"Jithin James, Luis Espinosa-Anke, Shahul Es, Steven Schockaert","cross_cats":[],"headline":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T19:23:54Z","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation"},"references":{"count":3,"internal_anchors":2,"resolved_work":3,"sample":[{"cited_arxiv_id":"2303.12712","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","work_id":"a23cfe92-7f7c-424b-98d4-b386a83002fb","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Halueval: A large-scale hallucination evaluation benchmark for large language models","work_id":"2cf6bc2d-aed3-4a58-879e-daf0de687940","year":2020},{"cited_arxiv_id":"2303.08896","doi":"","is_internal_anchor":true,"ref_index":3,"title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","work_id":"90efebf6-4006-4176-9bf1-21a876571751","year":2023}],"snapshot_sha256":"4e9839eed543571b87bdca218a259dada870540fa790eee7398efb59804fbf27"},"source":{"id":"2309.15217","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T21:33:03.116002Z","id":"7b8b1f3e-2760-402d-b137-0f8f35e51ae5","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ragas supplies reference-free metrics for measuring context relevance, faithfulness to retrieved passages, and answer quality in RAG pipelines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines.","strongest_claim":"We put forward a suite of metrics which can be used to evaluate these different dimensions without having to rely on ground truth human annotations.","weakest_assumption":"That LLM-based judgments of context relevance, faithfulness, and answer relevance will correlate sufficiently with human judgments across domains and models without additional calibration or validation data."}},"verdict_id":"7b8b1f3e-2760-402d-b137-0f8f35e51ae5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:548b25745cbbd07eb602e0c9477d52c41b1f76ed6950d602a67893b221f94e0a","target":"record","created_at":"2026-05-17T23:38:46Z","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":"007146ebe8160da410be50d017592d232248f0d29c844a95b1aa4da35c6cb3ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T19:23:54Z","title_canon_sha256":"91b21454bfac08ab0267ff0ab7c5697b9c78babb8efb3a88d2060faa54199c57"},"schema_version":"1.0","source":{"id":"2309.15217","kind":"arxiv","version":2}},"canonical_sha256":"527665b76865adfd4728c459c3beb358694b06fe0e9c77004eb0ebc4a2cdddcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527665b76865adfd4728c459c3beb358694b06fe0e9c77004eb0ebc4a2cdddcc","first_computed_at":"2026-05-17T23:38:46.488030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.488030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9cWV+o9hlRtiGOUWdeutf4o793lzpyBp8uN3cfZk4a+ZwDTZu1XlhMoTfK+25N4hSpYVuiL5YiNJ/NwhnO4mDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.488577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:548b25745cbbd07eb602e0c9477d52c41b1f76ed6950d602a67893b221f94e0a","sha256:8b08d53f92d32eb5af493b3d31351352b16696d08183f2c51a7afe25a61de696"],"state_sha256":"126673abd65f328e6cda2eda500c31be36dc7f9053fe1506f12b850cd24ecce1"}