{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KJ3GLN3IMWW72RZIYRM4HPVTLB","short_pith_number":"pith:KJ3GLN3I","schema_version":"1.0","canonical_sha256":"527665b76865adfd4728c459c3beb358694b06fe0e9c77004eb0ebc4a2cdddcc","source":{"kind":"arxiv","id":"2309.15217","version":2},"attestation_state":"computed","paper":{"title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jithin James, Luis Espinosa-Anke, Shahul Es, Steven Schockaert","submitted_at":"2023-09-26T19:23:54Z","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"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2309.15217","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-26T19:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"91b21454bfac08ab0267ff0ab7c5697b9c78babb8efb3a88d2060faa54199c57","abstract_canon_sha256":"007146ebe8160da410be50d017592d232248f0d29c844a95b1aa4da35c6cb3ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.488577Z","signature_b64":"9cWV+o9hlRtiGOUWdeutf4o793lzpyBp8uN3cfZk4a+ZwDTZu1XlhMoTfK+25N4hSpYVuiL5YiNJ/NwhnO4mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527665b76865adfd4728c459c3beb358694b06fe0e9c77004eb0ebc4a2cdddcc","last_reissued_at":"2026-05-17T23:38:46.488030Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.488030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jithin James, Luis Espinosa-Anke, Shahul Es, Steven Schockaert","submitted_at":"2023-09-26T19:23:54Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ragas supplies reference-free metrics for measuring context relevance, faithfulness to retrieved passages, and answer quality in RAG pipelines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e8604ffb2e1165e3985ff08277d4af73b8bd189af2184a600778006a75c32a97"},"source":{"id":"2309.15217","kind":"arxiv","version":2},"verdict":{"id":"7b8b1f3e-2760-402d-b137-0f8f35e51ae5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:33:03.116002Z","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.","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","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.","pith_extraction_headline":"Ragas supplies reference-free metrics that score context relevance, faithfulness to retrieved passages, and answer relevance in RAG pipelines."},"references":{"count":3,"sample":[{"doi":"","year":2022,"title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","work_id":"a23cfe92-7f7c-424b-98d4-b386a83002fb","ref_index":1,"cited_arxiv_id":"2303.12712","is_internal_anchor":true},{"doi":"","year":2020,"title":"Halueval: A large-scale hallucination evaluation benchmark for large language models","work_id":"2cf6bc2d-aed3-4a58-879e-daf0de687940","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","work_id":"90efebf6-4006-4176-9bf1-21a876571751","ref_index":3,"cited_arxiv_id":"2303.08896","is_internal_anchor":true}],"resolved_work":3,"snapshot_sha256":"4e9839eed543571b87bdca218a259dada870540fa790eee7398efb59804fbf27","internal_anchors":2},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a3f195451793100092dea034b102bece97ffd22a817852f739338ab1cfff9e1a"},"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":"2309.15217","created_at":"2026-05-17T23:38:46.488119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15217v2","created_at":"2026-05-17T23:38:46.488119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15217","created_at":"2026-05-17T23:38:46.488119+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJ3GLN3IMWW7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJ3GLN3IMWW72RZI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJ3GLN3I","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2510.08945","citing_title":"FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":164,"is_internal_anchor":true},{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2505.09339","citing_title":"RAG-Enabled Intent Reasoning for Application-Network Interaction","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18760","citing_title":"DOTRAG: Retrieval-Time Reasoning Along Paths","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19075","citing_title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01553","citing_title":"IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04936","citing_title":"Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29875","citing_title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22757","citing_title":"StratRAG: A Multi-Hop Retrieval Evaluation Dataset for Retrieval-Augmented Generation Systems","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2401.15391","citing_title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14488","citing_title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03174","citing_title":"Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26382","citing_title":"Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23515","citing_title":"ragR: Retrieval-Augmented Generation and RAG Assessment in R","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23366","citing_title":"GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19457","citing_title":"Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2404.16130","citing_title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07209","citing_title":"Hallucination Detection via Activations of Open-Weight Proxy Analyzers","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15945","citing_title":"RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16706","citing_title":"Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB","json":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB.json","graph_json":"https://pith.science/api/pith-number/KJ3GLN3IMWW72RZIYRM4HPVTLB/graph.json","events_json":"https://pith.science/api/pith-number/KJ3GLN3IMWW72RZIYRM4HPVTLB/events.json","paper":"https://pith.science/paper/KJ3GLN3I"},"agent_actions":{"view_html":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB","download_json":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB.json","view_paper":"https://pith.science/paper/KJ3GLN3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15217&json=true","fetch_graph":"https://pith.science/api/pith-number/KJ3GLN3IMWW72RZIYRM4HPVTLB/graph.json","fetch_events":"https://pith.science/api/pith-number/KJ3GLN3IMWW72RZIYRM4HPVTLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB/action/storage_attestation","attest_author":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB/action/author_attestation","sign_citation":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB/action/citation_signature","submit_replication":"https://pith.science/pith/KJ3GLN3IMWW72RZIYRM4HPVTLB/action/replication_record"}},"created_at":"2026-05-17T23:38:46.488119+00:00","updated_at":"2026-05-17T23:38:46.488119+00:00"}