{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UPD4GYNDJV7IGKBR57YZE2UHQB","short_pith_number":"pith:UPD4GYND","schema_version":"1.0","canonical_sha256":"a3c7c361a34d7e832831eff1926a878071ae9b001f1ec70dd563b5179be3f8e6","source":{"kind":"arxiv","id":"2407.11005","version":2},"attestation_state":"computed","paper":{"title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atindriyo Sanyal, Masha Belyi, Robert Friel","submitted_at":"2024-06-25T20:23:15Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a standard architectural pattern for incorporating domain-specific knowledge into user-facing chat applications powered by Large Language Models (LLMs). RAG systems are characterized by (1) a document retriever that queries a domain-specific corpus for context information relevant to an input query, and (2) an LLM that generates a response based on the provided query and context. However, comprehensive evaluation of RAG systems remains a challenge due to the lack of unified evaluation criteria and annotated datasets. In response, we introduce RAG"},"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":"2407.11005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T20:23:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b530857251c9883ccea7666d5f83ec240a5ef340fc62d58414a6dc63726144d","abstract_canon_sha256":"e777ae494c8869c6534c2d66f44f4d8387d01fdb54690d5f9b695a1efa2d9025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:34.582574Z","signature_b64":"ZHegmh6GCYNAPH++SwXFgB9n3dpUP6ZMN1hLuyzhaD/1nVFBaa8pWYSr9PLq27QyT7bGaGYKidLTKv/uP4JWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3c7c361a34d7e832831eff1926a878071ae9b001f1ec70dd563b5179be3f8e6","last_reissued_at":"2026-07-05T10:01:34.582125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:34.582125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atindriyo Sanyal, Masha Belyi, Robert Friel","submitted_at":"2024-06-25T20:23:15Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a standard architectural pattern for incorporating domain-specific knowledge into user-facing chat applications powered by Large Language Models (LLMs). RAG systems are characterized by (1) a document retriever that queries a domain-specific corpus for context information relevant to an input query, and (2) an LLM that generates a response based on the provided query and context. However, comprehensive evaluation of RAG systems remains a challenge due to the lack of unified evaluation criteria and annotated datasets. In response, we introduce RAG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11005","kind":"arxiv","version":2},"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/2407.11005/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":"2407.11005","created_at":"2026-07-05T10:01:34.582185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11005v2","created_at":"2026-07-05T10:01:34.582185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11005","created_at":"2026-07-05T10:01:34.582185+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPD4GYNDJV7I","created_at":"2026-07-05T10:01:34.582185+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPD4GYNDJV7IGKBR","created_at":"2026-07-05T10:01:34.582185+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPD4GYND","created_at":"2026-07-05T10:01:34.582185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06008","citing_title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06008","citing_title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21831","citing_title":"RAIDS: Rethinking Data Systems as Responsible Intelligent Infrastructure","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05901","citing_title":"Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04646","citing_title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30306","citing_title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30062","citing_title":"Little Brains, Big Feats: Exploring Compact Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27494","citing_title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27164","citing_title":"Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09174","citing_title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21102","citing_title":"ACL-Verbatim: hallucination-free question answering for research","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05257","citing_title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08919","citing_title":"LLMs as Assessors: Right for the Right Reason?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29875","citing_title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00964","citing_title":"Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12138","citing_title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12047","citing_title":"Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09174","citing_title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05244","citing_title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB","json":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB.json","graph_json":"https://pith.science/api/pith-number/UPD4GYNDJV7IGKBR57YZE2UHQB/graph.json","events_json":"https://pith.science/api/pith-number/UPD4GYNDJV7IGKBR57YZE2UHQB/events.json","paper":"https://pith.science/paper/UPD4GYND"},"agent_actions":{"view_html":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB","download_json":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB.json","view_paper":"https://pith.science/paper/UPD4GYND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11005&json=true","fetch_graph":"https://pith.science/api/pith-number/UPD4GYNDJV7IGKBR57YZE2UHQB/graph.json","fetch_events":"https://pith.science/api/pith-number/UPD4GYNDJV7IGKBR57YZE2UHQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB/action/storage_attestation","attest_author":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB/action/author_attestation","sign_citation":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB/action/citation_signature","submit_replication":"https://pith.science/pith/UPD4GYNDJV7IGKBR57YZE2UHQB/action/replication_record"}},"created_at":"2026-07-05T10:01:34.582185+00:00","updated_at":"2026-07-05T10:01:34.582185+00:00"}